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. 19-RESID-POST-AA
    6. 127463
    Prev
    Next
    INDEX
    Explanations

    Rapaport, abbreviations, names

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     体
    -0.06
    .secret
    -0.06
     множе
    -0.06
     Thou
    -0.06
     Be
    -0.06
     minimize
    -0.06
     Isa
    -0.06
     MR
    -0.05
     overcoming
    -0.05
     хозя
    -0.05
    POSITIVE LOGITS
    901
    0.07
    acey
    0.07
    _plots
    0.07
    prs
    0.07
    Accessor
    0.07
    Ipv
    0.07
    스
    0.07
    _DISPLAY
    0.07
     calc
    0.06
    Blockchain
    0.06
    Activations Density 0.020%

    No Known Activations