© 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
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 93947
    Prev
    Next
    INDEX
    Explanations

    scientific research

    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
     receptor
    -0.11
     proteins
    -0.11
     protein
    -0.10
     peptide
    -0.10
     apoptosis
    -0.10
     mutant
    -0.10
     cells
    -0.10
     RNA
    -0.10
     receptors
    -0.10
     apopt
    -0.09
    POSITIVE LOGITS
     Hòa
    0.06
    -Semit
    0.06
     hry
    0.06
     jul
    0.06
     dua
    0.06
    .menu
    0.06
    QString
    0.06
    有的
    0.06
    NdEx
    0.06
    _strerror
    0.06
    Activations Density 0.865%

    No Known Activations