© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 7901
    Prev
    Next
    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash

    The neuron activates on the “by” (and surrounding structure) in song‐title attributions (i.e. the “song” by “artist” pattern).

    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
     बच
    -0.07
     CLASS
    -0.06
    _ctrl
    -0.06
     withdrawal
    -0.06
     kale
    -0.06
    detach
    -0.06
    ierrez
    -0.06
     pairing
    -0.06
     derail
    -0.06
     Fits
    -0.06
    POSITIVE LOGITS
    __*/
    0.07
    89
    0.07
    竹
    0.06
     прояв
    0.06
     africa
    0.06
     performing
    0.06
     gobierno
    0.06
    45
    0.06
     Spider
    0.06
    ptides
    0.06
    Activations Density 0.005%

    No Known Activations