© 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. 37107
    Prev
    Next
    INDEX
    Explanations

    a

    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
    /h
    -0.07
    半
    -0.07
    จากการ
    -0.06
     اختص
    -0.06
    MeshPro
    -0.06
    948
    -0.06
    itesi
    -0.06
     Reads
    -0.06
    668
    -0.06
    уются
    -0.06
    POSITIVE LOGITS
    feedback
    0.07
     contraception
    0.07
    (flow
    0.07
    .getLongitude
    0.06
     unpaid
    0.06
    .dequeueReusableCell
    0.06
     gest
    0.06
    uge
    0.06
     instructions
    0.06
    (dm
    0.06
    Activations Density 0.140%

    No Known Activations