© 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. 71673
    Prev
    Next
    INDEX
    Explanations

    location and time references

    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
    temp
    -0.07
     العق
    -0.07
    —not
    -0.06
    ">'
    -0.06
    Ham
    -0.06
     Lester
    -0.06
    _station
    -0.06
    ВС
    -0.06
     다음과
    -0.06
    Це
    -0.06
    POSITIVE LOGITS
    /tcp
    0.07
    ornings
    0.06
    (ERR
    0.06
     krit
    0.06
     lược
    0.06
     başlan
    0.06
    トリ
    0.06
    bane
    0.06
    boxing
    0.06
     formatDate
    0.06
    Activations Density 0.022%

    No Known Activations