© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 12770
    Prev
    Next
    INDEX
    Explanations

    reruns

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of TV re-airings—words like “repeat,” “reruns,” “re-air,” etc.

    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
    け
    -0.06
    Sig
    -0.06
     Twelve
    -0.06
     alist
    -0.06
     circum
    -0.06
     olup
    -0.06
     Ya
    -0.06
     lah
    -0.06
     NL
    -0.06
     Burke
    -0.06
    POSITIVE LOGITS
    informatics
    0.06
     україн
    0.06
     mga
    0.06
    .netflix
    0.06
    AccessException
    0.06
    ς
    0.06
     Tuy
    0.06
    (())↵
    0.06
    getOption
    0.06
    ListItemIcon
    0.06
    Activations Density 0.021%

    No Known Activations