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. 9763
    Prev
    Next
    INDEX
    Explanations

    punctuation and connectors

    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
    における
    -0.06
     Suz
    -0.06
     개인
    -0.06
    Mbps
    -0.06
    (guild
    -0.06
     CH
    -0.06
     리그
    -0.06
    ]._
    -0.06
    економ
    -0.06
    řev
    -0.05
    POSITIVE LOGITS
    -income
    0.08
    сутств
    0.07
     XMLHttpRequest
    0.07
    _arguments
    0.07
     unaffected
    0.07
    飯
    0.07
    _METADATA
    0.07
     *(*
    0.07
    igrated
    0.07
    .Unmarshal
    0.07
    Activations Density 0.000%

    No Known Activations