© 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. 129107
    Prev
    Next
    INDEX
    Explanations

    _am

    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
     sociale
    -0.07
     :=
    -0.07
    .keras
    -0.07
    _managed
    -0.07
    ULD
    -0.06
    -boot
    -0.06
     richest
    -0.06
    _ro
    -0.06
    _le
    -0.06
    _tweets
    -0.06
    POSITIVE LOGITS
     ApiResponse
    0.06
    Methods
    0.06
     Tus
    0.06
     BD
    0.06
    bestos
    0.06
    航
    0.06
     kênh
    0.05
    (dm
    0.05
    ��
    0.05
     तर
    0.05
    Activations Density 0.013%

    No Known Activations