© 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. 93261
    Prev
    Next
    INDEX
    Explanations

    Law/Constitution

    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
     जन
    -0.07
    віль
    -0.07
     estruct
    -0.06
     Lost
    -0.06
     faced
    -0.06
    ,new
    -0.06
    �
    -0.06
     plutôt
    -0.06
    gt
    -0.06
    tres
    -0.06
    POSITIVE LOGITS
     injection
    0.07
    \Model
    0.07
     },↵
    0.07
    .Σ
    0.07
    .Sn
    0.07
    ای
    0.06
     yaw
    0.06
     battleground
    0.06
     Fehler
    0.06
    Mappings
    0.06
    Activations Density 0.047%

    No Known Activations