© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 36943
    Prev
    Next
    INDEX
    Explanations

    MIDI

    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
    Mismatch
    -0.07
     Linear
    -0.06
    \Storage
    -0.06
     милли
    -0.06
    ิล
    -0.06
     Fax
    -0.06
    ErrMsg
    -0.06
     Followers
    -0.06
    acam
    -0.05
     hair
    -0.05
    POSITIVE LOGITS
    ando
    0.07
    .Retrofit
    0.06
     مسجد
    0.06
     sạn
    0.06
    .navigationItem
    0.06
     obtaining
    0.06
    ,j
    0.06
    .isSuccessful
    0.06
    พวก
    0.06
    _strategy
    0.06
    Activations Density 0.014%

    No Known Activations