© 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. 73048
    Prev
    Next
    INDEX
    Explanations

    feasibility

    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
    rir
    -0.07
     �
    -0.07
    ?>
    -0.07
     Scho
    -0.06
     characterization
    -0.06
     minorities
    -0.06
    Reporting
    -0.06
     serves
    -0.06
     neighb
    -0.06
    OLER
    -0.06
    POSITIVE LOGITS
     feasibility
    0.08
     Flight
    0.07
    ทะ
    0.07
     feasible
    0.07
     Melbourne
    0.07
    tiv
    0.07
     ره
    0.07
     IBM
    0.06
     것
    0.06
    (LL
    0.06
    Activations Density 0.011%

    No Known Activations