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. 128767
    Prev
    Next
    INDEX
    Explanations

    acic

    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
     Gor
    -0.08
     Founded
    -0.07
     Triangle
    -0.06
     تأثیر
    -0.06
     miscon
    -0.06
    drs
    -0.06
    -deals
    -0.06
    _byte
    -0.06
    .К
    -0.06
     Edinburgh
    -0.06
    POSITIVE LOGITS
    uid
    0.06
    .textBox
    0.06
    customerId
    0.06
    ας
    0.06
     seksi
    0.06
     vestib
    0.06
     siz
    0.06
    장은
    0.06
    gio
    0.06
     upro
    0.06
    Activations Density 0.004%

    No Known Activations