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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 110001
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron fires on verbs (especially “try,” “connect,” “install,” “update,” etc.) and the infinitival “to,” i.e. on tokens that signal an attempted action.

    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
     squeezing
    -0.07
    .Should
    -0.07
     hits
    -0.07
     BL
    -0.07
    Position
    -0.06
    ests
    -0.06
    FindBy
    -0.06
     assembling
    -0.06
    .Selection
    -0.06
    ecz
    -0.06
    POSITIVE LOGITS
     indiv
    0.07
     NullPointerException
    0.06
     mike
    0.06
     fich
    0.06
    '
    ↵
    ↵
    0.06
     учит
    0.06
    )),
    ↵
    0.06
     takeover
    0.06
    roma
    0.06
    afür
    0.06
    Activations Density 0.076%

    No Known Activations