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. 10347
    Prev
    Next
    INDEX
    Explanations

    description

    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
    -products
    -0.07
     les
    -0.07
     Zeit
    -0.07
    Large
    -0.07
     stata
    -0.07
    _SHOW
    -0.06
     petite
    -0.06
    (editor
    -0.06
    Cas
    -0.06
     Palestin
    -0.06
    POSITIVE LOGITS
    ैं।↵
    0.07
    	sf
    0.06
     것으로
    0.06
     qualifies
    0.06
    arrival
    0.06
    _DST
    0.06
    	pw
    0.06
     ace
    0.06
    DSA
    0.06
     terrified
    0.06
    Activations Density 0.001%

    No Known Activations