Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 1516
    Prev
    Next
    INDEX
    Explanations

    code redirection

    np_max-act · gemini-2.0-flash

    code snippets and instructions related to user authentication and session management in web applications.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on code tokens that perform HTTP redirects (e.g. “redirect_to”, “redirect to”, location headers), i.e. redirect statements.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fourteen
    -0.07
    饮
    -0.07
    highlight
    -0.06
     recordings
    -0.06
     dě
    -0.06
    unprocessable
    -0.06
    krát
    -0.06
     Sosyal
    -0.06
    -remove
    -0.06
     Cup
    -0.06
    POSITIVE LOGITS
    Jake
    0.07
     Lebanon
    0.07
     heatmap
    0.06
    .hs
    0.06
     deprecated
    0.06
     lh
    0.06
    |-
    0.06
    Country
    0.06
     ^=
    0.06
     charities
    0.06
    Activations Density 0.004%

    No Known Activations