© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 51963
    Prev
    Next
    INDEX
    Explanations

    travel

    np_max-act · gemini-2.0-flash

    references to political or diplomatic events involving international relations.

    oai_token-act-pair · gpt-4o-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
     Protection
    -0.07
    ťan
    -0.07
    caffe
    -0.07
    ارج
    -0.06
     isolated
    -0.06
    ott
    -0.06
    iểu
    -0.06
    occan
    -0.06
     canopy
    -0.06
    imore
    -0.06
    POSITIVE LOGITS
    ',(
    0.07
     ребенка
    0.07
     incorporates
    0.07
    asurement
    0.07
    ->{_
    0.07
    CLOCKS
    0.07
    _on
    0.07
    ************************
    0.06
    .bid
    0.06
    _ISS
    0.06
    Activations Density 0.036%

    No Known Activations