© 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. 100148
    Prev
    Next
    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    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
     Seznam
    -0.07
    यह
    -0.07
    Lambda
    -0.06
     eiusmod
    -0.06
    Road
    -0.06
    collapsed
    -0.06
    xmm
    -0.06
     одерж
    -0.06
    RequestMapping
    -0.06
    ']):
    -0.06
    POSITIVE LOGITS
     that
    0.08
     THAT
    0.07
     noi
    0.07
    that
    0.06
    	error
    0.06
    <_
    0.06
     бук
    0.06
     imposs
    0.06
    $name
    0.06
    _k
    0.06
    Activations Density 0.033%

    No Known Activations