© 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. 121864
    Prev
    Next
    INDEX
    Explanations

    local

    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
     Renaissance
    -0.07
    .OneToOne
    -0.07
    CON
    -0.06
    576
    -0.06
    owania
    -0.06
    ije
    -0.06
    _sizes
    -0.06
    phant
    -0.06
    rotation
    -0.06
     Access
    -0.06
    POSITIVE LOGITS
     local
    0.08
    _locals
    0.06
     refute
    0.06
     Compiled
    0.06
     tutorials
    0.06
     socio
    0.06
     mouseX
    0.06
    큼
    0.06
     ê
    0.06
     poh
    0.06
    Activations Density 0.007%

    No Known Activations