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. 13953
    Prev
    Next
    INDEX
    Explanations

    legal documents

    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
     Lump
    -0.07
    avers
    -0.06
    480
    -0.06
    Bubble
    -0.06
     denominator
    -0.06
    .setUser
    -0.06
    �
    -0.06
     attached
    -0.06
    σει
    -0.06
     tunes
    -0.06
    POSITIVE LOGITS
     количества
    0.07
     peri
    0.07
     současné
    0.07
    .union
    0.07
     ("\
    0.07
    (td
    0.06
     название
    0.06
    _ls
    0.06
     Paw
    0.06
    FileChooser
    0.06
    Activations Density 0.053%

    No Known Activations