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. 69604
    Prev
    Next
    INDEX
    Explanations

    ness

    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
    i
    -0.08
    Io
    -0.08
    il
    -0.07
    'It
    -0.07
     prote
    -0.07
    Orm
    -0.07
     principal
    -0.07
    *l
    -0.06
     el
    -0.06
    ali
    -0.06
    POSITIVE LOGITS
    ness
    0.16
    eness
    0.14
    NESS
    0.13
    iveness
    0.12
    iness
    0.11
     Madness
    0.10
    ess
    0.10
     goodness
    0.09
     effectiveness
    0.09
     randomness
    0.09
    Activations Density 0.037%

    No Known Activations