© 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. 6896
    Prev
    Next
    INDEX
    Explanations

    Concerns

    np_max-act · gemini-2.0-flash

    The neuron detects language used in safety‐oriented disclaimers—phrases that invite or express user concerns.

    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
     scm
    -0.07
     eks
    -0.07
     goog
    -0.07
    RoleId
    -0.07
    Cancelar
    -0.07
     FORWARD
    -0.06
    ensis
    -0.06
     fas
    -0.06
     Vys
    -0.06
    、お
    -0.06
    POSITIVE LOGITS
     Nik
    0.06
     elect
    0.06
     Pik
    0.06
    ánd
    0.06
    _success
    0.06
     LP
    0.06
     DK
    0.06
     SP
    0.06
    情况
    0.06
    زب
    0.06
    Activations Density 0.018%

    No Known Activations