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. 84357
    Prev
    Next
    INDEX
    Explanations

    to/not

    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
    lation
    -0.06
    ätz
    -0.06
    ždy
    -0.06
     vše
    -0.06
     bacon
    -0.06
    اذا
    -0.05
     ET
    -0.05
     unterstüt
    -0.05
    bz
    -0.05
    '))↵
    -0.05
    POSITIVE LOGITS
    Rightarrow
    0.07
    GuidId
    0.07
    /mp
    0.07
     Berkshire
    0.06
     trays
    0.06
     reside
    0.06
    _FRIEND
    0.06
     nons
    0.06
     веществ
    0.06
     leurs
    0.06
    Activations Density 0.002%

    No Known Activations