© 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. 92623
    Prev
    Next
    INDEX
    Explanations

    activation

    np_max-act · gemini-2.0-flash

    This neuron fires on occurrences of “activ-” (e.g. activation, activate, activating) and related morphological forms.

    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
     Table
    -0.08
     sample
    -0.07
    俗
    -0.07
     tale
    -0.07
    (Page
    -0.07
     err
    -0.07
     pockets
    -0.07
    Wide
    -0.07
     note
    -0.07
     müm
    -0.07
    POSITIVE LOGITS
     activated
    0.10
     activation
    0.10
     Activ
    0.09
    ovic
    0.08
    _ACTIV
    0.08
     activ
    0.08
     activate
    0.08
     canActivate
    0.08
    ayın
    0.08
     activist
    0.08
    Activations Density 0.021%

    No Known Activations