© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 13182
    Prev
    Next
    INDEX
    Explanations

    Resize

    np_max-act · gemini-2.0-flash

    code-related terminology and functions associated with resizing elements or images in programming contexts.

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

    The neuron flags code tokens containing the substring “resiz” (e.g. “Resize,” “resizable,” “resize,” etc.).

    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
     sublicense
    -0.07
     Cert
    -0.07
     друг
    -0.07
     pot
    -0.06
     unit
    -0.06
    .Space
    -0.06
     plaint
    -0.06
     Blood
    -0.06
    .todos
    -0.06
     출력
    -0.06
    POSITIVE LOGITS
    Resize
    0.08
     resize
    0.08
     resizing
    0.08
     resized
    0.08
     Resize
    0.07
     resh
    0.07
     remodeling
    0.07
    .Resize
    0.07
    ixo
    0.07
    resize
    0.07
    Activations Density 0.003%

    No Known Activations