Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 15-RESID-POST-AA
    6. 128216
    Prev
    Next
    INDEX
    Explanations

    software tests and code

    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
    andi
    -0.07
     Λα
    -0.06
     rigs
    -0.06
     grave
    -0.06
    тю
    -0.06
    edge
    -0.06
    ается
    -0.06
     Alien
    -0.06
                            
    -0.06
    わたし
    -0.05
    POSITIVE LOGITS
     Surgery
    0.08
     utiliser
    0.07
     LOCATION
    0.07
     Shotgun
    0.07
    .textColor
    0.07
    .position
    0.06
     vd
    0.06
    _STENCIL
    0.06
    atoms
    0.06
     Miracle
    0.06
    Activations Density 0.000%

    No Known Activations