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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 84594
    Prev
    Next
    INDEX
    Explanations

    -bin

    np_max-act · gemini-2.0-flash

    The neuron fires on fragments of “/cgi-bin” URLs, i.e. links pointing to CGI script endpoints.

    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
    .metro
    -0.07
     详情
    -0.07
    ')}}
    -0.07
    (book
    -0.07
     Still
    -0.07
    -divider
    -0.07
     explode
    -0.07
    >]
    -0.07
     />);↵
    -0.06
     organisations
    -0.06
    POSITIVE LOGITS
    -bin
    0.08
     قائمة
    0.07
    _View
    0.07
     Bin
    0.07
    _vert
    0.06
    mour
    0.06
    INC
    0.06
    良
    0.06
    _MIN
    0.06
     Technique
    0.06
    Activations Density 0.000%

    No Known Activations