Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 93331
    Prev
    Next
    INDEX
    Explanations

    entionPolicy

    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
    ποίηση
    -0.07
     کود
    -0.07
     آغاز
    -0.07
    _REC
    -0.07
     Johnson
    -0.07
     Cubs
    -0.07
    HOOK
    -0.06
     Kelly
    -0.06
     potřeb
    -0.06
     louis
    -0.06
    POSITIVE LOGITS
    entionPolicy
    0.15
    ValueHandling
    0.09
    .runners
    0.09
    Handling
    0.07
    -animate
    0.07
    .'),↵
    0.06
     매
    0.06
     =&
    0.06
    ';↵↵
    0.06
    anner
    0.06
    Activations Density 0.000%

    No Known Activations