© 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. 106673
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
    'http
    -0.06
     pacing
    -0.06
     luxurious
    -0.06
    420
    -0.06
     turnover
    -0.06
    φ
    -0.06
     einen
    -0.06
    -owner
    -0.06
    BJ
    -0.06
    clients
    -0.06
    POSITIVE LOGITS
    ША
    0.06
    ×</
    0.06
    LDAP
    0.06
     çıktı
    0.06
    thanks
    0.06
    .getInput
    0.06
    amient
    0.06
     vec
    0.06
     FLAC
    0.06
     \"{
    0.06
    Activations Density 0.058%

    No Known Activations