Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 81363
    Prev
    Next
    INDEX
    Explanations

    investigation

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of formal investigations or investigative actions (e.g., “investigation,” “investigations”) by authorities or law‐enforcement bodies.

    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
    _tC
    -0.07
     cfg
    -0.06
    iy
    -0.06
     효
    -0.06
    atics
    -0.06
     magistrate
    -0.06
     TH
    -0.06
     TMP
    -0.06
    tones
    -0.06
    uder
    -0.06
    POSITIVE LOGITS
    announcement
    0.08
     investigation
    0.07
     findAll
    0.07
    .report
    0.07
     radioactive
    0.07
    ноз
    0.07
    	uv
    0.07
     Architects
    0.06
    querySelector
    0.06
    idunt
    0.06
    Activations Density 0.010%

    No Known Activations