© 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. 90916
    Prev
    Next
    INDEX
    Explanations

    legal complaints/investigations

    np_max-act · gemini-2.0-flash

    Neuron 4 responds to words and short phrases that denote legal or regulatory enforcement actions (e.g. complaint, investigation, notice, case, objections).

    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
    anky
    -0.07
    ash
    -0.07
    isValid
    -0.06
    _CHUNK
    -0.06
    _NOT
    -0.06
    导致
    -0.06
    OLOR
    -0.06
    ारक
    -0.06
     Vendor
    -0.06
     MED
    -0.06
    POSITIVE LOGITS
    =add
    0.07
     Coca
    0.06
    tan
    0.06
    入れ
    0.06
    Britain
    0.06
    0.06
    ctor
    0.06
     cứu
    0.06
     Farmer
    0.06
    izzard
    0.06
    Activations Density 0.011%

    No Known Activations