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. 15-RESID-POST-AA
    6. 121153
    Prev
    Next
    INDEX
    Explanations

    her

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Correspond
    -0.07
     Alcohol
    -0.07
     inquiries
    -0.06
     Discussions
    -0.06
    /op
    -0.06
     орг
    -0.06
    كر
    -0.06
    kind
    -0.06
     τι
    -0.06
    Acknowled
    -0.06
    POSITIVE LOGITS
    .transforms
    0.06
    有限
    0.06
     funkc
    0.06
    _vs
    0.06
     DVDs
    0.06
    -devel
    0.06
    askan
    0.06
    -lived
    0.05
    /Add
    0.05
    -table
    0.05
    Activations Density 0.001%

    No Known Activations