© 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. 7-RESID-POST-AA
    11. 28017
    Prev
    Next
    INDEX
    Explanations

    more

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     něho
    -0.07
     Landscape
    -0.07
     Regards
    -0.07
     oa
    -0.07
    hf
    -0.06
    “你
    -0.06
     contexto
    -0.06
     Stephens
    -0.06
     bezpečnost
    -0.06
    -threatening
    -0.06
    POSITIVE LOGITS
     torture
    0.07
     ****************************************************************
    0.07
    Cached
    0.07
    "",↵
    0.06
     fulfilling
    0.06
     reserved
    0.06
    ********
    0.06
    .dump
    0.06
     bookings
    0.06
    .getResource
    0.06
    Activations Density 0.008%

    No Known Activations