© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 56075
    Prev
    Next
    INDEX
    Explanations

    technical descriptions/titles

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     muff
    -0.06
    .JsonIgnore
    -0.06
    apor
    -0.06
     dosy
    -0.06
    ITLE
    -0.05
    Arg
    -0.05
     MA
    -0.05
     Download
    -0.05
     humano
    -0.05
    _LS
    -0.05
    POSITIVE LOGITS
     香
    0.07
    ）。↵↵
    0.07
    个人
    0.07
     illustration
    0.07
     comfortable
    0.07
     εν
    0.06
    symbols
    0.06
     الدر
    0.06
    ]:
    0.06
    егод
    0.06
    Activations Density 0.079%

    No Known Activations