© 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. 3-RESID-POST-AA
    11. 94104
    Prev
    Next
    INDEX
    Explanations

    on

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _requires
    -0.06
                    
    -0.06
     remar
    -0.06
    75
    -0.06
    (HTTP
    -0.06
     crate
    -0.06
    (uid
    -0.06
    (emp
    -0.06
    ip
    -0.06
    _department
    -0.06
    POSITIVE LOGITS
    vell
    0.07
     Paran
    0.07
     dateTime
    0.06
     rewarded
    0.06
    گذ
    0.06
     فض
    0.06
    _Float
    0.06
    .cast
    0.06
    _Page
    0.06
     conceal
    0.06
    Activations Density 0.008%

    No Known Activations