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. 112922
    Prev
    Next
    INDEX
    Explanations

    ensitive

    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
     substitutions
    -0.07
     têm
    -0.07
    _TEST
    -0.07
     уж
    -0.06
    Seven
    -0.06
    -search
    -0.06
     locker
    -0.06
     Riy
    -0.06
    opa
    -0.06
    ection
    -0.06
    POSITIVE LOGITS
    �
    0.08
    ・━・━・━・━
    0.07
    (country
    0.07
     Instituto
    0.06
     kindness
    0.06
     healthcare
    0.06
    conomy
    0.06
    (Packet
    0.06
    ICO
    0.06
    董事
    0.06
    Activations Density 0.005%

    No Known Activations