© 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. 239
    Prev
    Next
    INDEX
    Explanations

    mom

    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
     Ngọc
    -0.07
     dấu
    -0.07
     Ragnar
    -0.07
    )){↵↵
    -0.06
     Adding
    -0.06
     př
    -0.06
    whose
    -0.06
    bdd
    -0.06
     �
    -0.06
     Ром
    -0.06
    POSITIVE LOGITS
    ạt
    0.07
    ambient
    0.06
    eshire
    0.06
    297
    0.06
    €™
    0.06
     edil
    0.06
     생산
    0.06
    Override
    0.06
    ี,
    0.06
     hepatitis
    0.06
    Activations Density 0.000%

    No Known Activations