© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 6924
    Prev
    Next
    INDEX
    Explanations

    investment

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of “investment” (and its morphological variants like “investing,” “investments,” 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
     zf
    -0.07
    Decode
    -0.07
    .Cookies
    -0.06
    strar
    -0.06
    .cfg
    -0.06
    .effect
    -0.06
    (mat
    -0.06
    _bootstrap
    -0.06
    errs
    -0.06
    (:
    -0.06
    POSITIVE LOGITS
     investment
    0.09
     Investment
    0.08
     mischief
    0.07
     hometown
    0.07
     increase
    0.07
    �
    0.06
    nicos
    0.06
     留
    0.06
    ship
    0.06
    multi
    0.06
    Activations Density 0.008%

    No Known Activations