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. 11-RESID-POST-AA
    6. 1205
    Prev
    Next
    INDEX
    Explanations

    Music covers/remakes

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of “cover” and related forms (e.g. covering, cover versions), i.e. references to cover songs.

    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
    GameData
    -0.07
    	addr
    -0.06
     synthesis
    -0.06
     Loves
    -0.06
    Fuck
    -0.06
     Emblem
    -0.06
     onTap
    -0.06
    Sizes
    -0.06
    	save
    -0.06
    ルト
    -0.06
    POSITIVE LOGITS
    .FlatAppearance
    0.07
     cautious
    0.07
    _principal
    0.07
    .twimg
    0.06
    Modified
    0.06
    //
    0.06
    ظˆط
    0.06
    bond
    0.06
    _extend
    0.06
     pož
    0.06
    Activations Density 0.059%

    No Known Activations