© 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
    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. 92538
    Prev
    Next
    INDEX
    Explanations

    move

    np_max-act · gemini-2.0-flash

    The neuron lights up on instances of the verb “move” (e.g. “moving,” “move”) in the text.

    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
    ランド
    -0.07
     Canterbury
    -0.06
    Shell
    -0.06
    fort
    -0.06
     cầu
    -0.06
     Cal
    -0.06
     alph
    -0.06
     California
    -0.06
    ARCH
    -0.06
     beh
    -0.06
    POSITIVE LOGITS
     move
    0.17
     moving
    0.15
     moves
    0.13
     Move
    0.13
     Moving
    0.12
    Move
    0.12
    Moved
    0.12
    moving
    0.11
    	move
    0.11
     movement
    0.11
    Activations Density 0.050%

    No Known Activations