© 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. 15-RESID-POST-AA
    11. 57182
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     připrav
    -0.07
     Sponsor
    -0.07
     influx
    -0.07
     现
    -0.06
     bumped
    -0.06
    xfe
    -0.06
     Tut
    -0.06
     mandated
    -0.06
     pathMatch
    -0.06
     consultations
    -0.06
    POSITIVE LOGITS
    .Mesh
    0.06
    Middle
    0.06
     Nicar
    0.06
     nesting
    0.06
    lias
    0.06
    780
    0.06
    ***↵↵
    0.06
     Giáo
    0.06
    accuracy
    0.06
    GtkWidget
    0.06
    Activations Density 0.001%

    No Known Activations