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

    Neuronpedia

    APICircuit 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. 11-RESID-POST-AA
    6. 84483
    Prev
    Next
    INDEX
    Explanations

    Music set lists

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of live music performances and set lists (e.g., “tour,” “set,” “concert,” “encore”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ेच
    -0.07
    bor
    -0.06
     Deutsch
    -0.06
     meth
    -0.06
    yg
    -0.06
    imiento
    -0.06
     skills
    -0.06
     ReadOnly
    -0.06
    आई
    -0.06
    ола
    -0.06
    POSITIVE LOGITS
     bryster
    0.07
     ".$
    0.07
     AUTO
    0.07
    ujete
    0.06
     declaration
    0.06
    ….↵↵
    0.06
    ::$
    0.06
    ertificate
    0.06
     преп
    0.06
    ่อไป
    0.06
    Activations Density 0.016%

    No Known Activations