© 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. 119043
    Prev
    Next
    INDEX
    Explanations

    blog-like text

    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
    ekk
    -0.06
    qe
    -0.06
     Çev
    -0.06
    ajas
    -0.06
    átel
    -0.06
    سین
    -0.06
    에
    -0.05
     Shah
    -0.05
     turist
    -0.05
    NER
    -0.05
    POSITIVE LOGITS
     getS
    0.07
     Initialization
    0.06
    uced
    0.06
     Meditation
    0.06
    好
    0.06
    énom
    0.06
     gluc
    0.06
     Fundamental
    0.06
     /*#__
    0.06
    _chart
    0.06
    Activations Density 0.465%

    No Known Activations