© 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. 42526
    Prev
    Next
    INDEX
    Explanations

    rolling or Roll*

    np_max-act · gemini-2.0-flash

    The neuron consistently lights up on occurrences of the “roll” morpheme (e.g. roll, roll-up, rolling).

    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
     sight
    -0.08
    inux
    -0.08
     danger
    -0.07
     fear
    -0.07
     cancer
    -0.07
     protect
    -0.07
     Cancer
    -0.07
     Jen
    -0.07
    _center
    -0.06
    ucose
    -0.06
    POSITIVE LOGITS
     Roll
    0.14
    Roll
    0.14
     roll
    0.13
     rolls
    0.13
    -roll
    0.12
     rolled
    0.11
    rollback
    0.10
     Rolling
    0.10
     rollout
    0.10
     Roland
    0.10
    Activations Density 0.014%

    No Known Activations