© 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. 41514
    Prev
    Next
    INDEX
    Explanations

    internet forum text

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on words related to funding or financial support (e.g. “self-fund,” “fund,” “fees”).

    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
    ,left
    -0.06
    (Profile
    -0.06
    Iteration
    -0.06
     petals
    -0.06
     eid
    -0.06
    HANDLE
    -0.06
    .toFloat
    -0.06
    _four
    -0.06
    afd
    -0.06
    .recycle
    -0.06
    POSITIVE LOGITS
    collect
    0.07
     specialize
    0.07
     stør
    0.07
    	NS
    0.07
    лек
    0.06
    amente
    0.06
     siyas
    0.06
    nt
    0.06
    kish
    0.06
    yw
    0.06
    Activations Density 0.147%

    No Known Activations