© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 123283
    Prev
    Next
    INDEX
    Explanations

    importance

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     distribution
    -0.06
     distributions
    -0.06
    basis
    -0.06
    isia
    -0.06
    .phase
    -0.06
    _parm
    -0.06
     gere
    -0.06
    بن
    -0.06
     Martha
    -0.06
     Veronica
    -0.06
    POSITIVE LOGITS
    _detach
    0.07
     Chinese
    0.07
    onnement
    0.07
    mouseout
    0.06
     homem
    0.06
     Freed
    0.06
     Spec
    0.06
     ignite
    0.06
    
    0.06
     Need
    0.06
    Activations Density 0.076%

    No Known Activations