© 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. 7964
    Prev
    Next
    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash

    The neuron is attuned to terms related to tree data‐structure elements—like root, leaf, node, and internal.

    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
     ToDo
    -0.06
    downloads
    -0.06
     maze
    -0.06
     harassment
    -0.06
    parated
    -0.06
    _prep
    -0.06
    658
    -0.06
    .reload
    -0.06
    /browser
    -0.06
    Queen
    -0.06
    POSITIVE LOGITS
     lifting
    0.07
    .Index
    0.07
    Photo
    0.07
    以下
    0.07
    _SITE
    0.07
     largest
    0.07
     exploring
    0.07
     \'
    0.06
    -label
    0.06
    lication
    0.06
    Activations Density 0.340%

    No Known Activations