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. 10234
    Prev
    Next
    INDEX
    Explanations

    Emergency medical services

    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
     ink
    -0.06
     find
    -0.06
     Benz
    -0.06
     jumps
    -0.06
     fois
    -0.06
     Kardash
    -0.06
    =get
    -0.06
    -being
    -0.06
     GPS
    -0.06
     faaliyet
    -0.06
    POSITIVE LOGITS
    JsonValue
    0.07
    .Submit
    0.07
    _temperature
    0.06
     Fuse
    0.06
     sectional
    0.06
    ATIONAL
    0.06
    Declared
    0.06
    .CustomButton
    0.06
    terminate
    0.06
    .dirty
    0.06
    Activations Density 0.007%

    No Known Activations