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. 7-RESID-POST-AA
    6. 100715
    Prev
    Next
    INDEX
    Explanations

    inexpensive and simple

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    üler
    -0.07
     clipboard
    -0.07
     inté
    -0.07
    (argument
    -0.06
    алів
    -0.06
    reb
    -0.06
    _subject
    -0.06
    .overlay
    -0.06
     збільш
    -0.06
     sms
    -0.06
    POSITIVE LOGITS
     поскольку
    0.08
     protože
    0.07
    .localScale
    0.07
    chio
    0.06
     flirting
    0.06
     Gomez
    0.06
    _PULL
    0.06
    简
    0.06
     вообще
    0.06
     rigs
    0.06
    Activations Density 0.036%

    No Known Activations