Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 92985
    Prev
    Next
    INDEX
    Explanations

    middle

    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
     scam
    -0.07
    áf
    -0.07
     enthusiasts
    -0.06
    _locale
    -0.06
     flaw
    -0.06
    uru
    -0.06
     boosted
    -0.06
     과
    -0.06
     Unlimited
    -0.06
    .GetComponent
    -0.06
    POSITIVE LOGITS
     middle
    0.17
     Middle
    0.17
    Middle
    0.15
    middle
    0.14
    -middle
    0.11
    .Middle
    0.10
    .middle
    0.09
    addle
    0.09
    IDDLE
    0.09
     Mitt
    0.09
    Activations Density 0.008%

    No Known Activations