© 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. 537
    Prev
    Next
    INDEX
    Explanations

    get

    np_max-act · gemini-2.0-flash

    conversations or contexts that involve manipulative or deceitful behaviors within relationships.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron never activates on any token, i.e. it does not detect any specific pattern.

    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
    boru
    -0.08
     Filtering
    -0.07
     Uph
    -0.07
     Lia
    -0.06
     mourn
    -0.06
    summer
    -0.06
     علی
    -0.06
     план
    -0.06
    LN
    -0.06
     borrowing
    -0.05
    POSITIVE LOGITS
    rost
    0.07
    равиль
    0.07
    )arg
    0.06
     getData
    0.06
    -clean
    0.06
    _RED
    0.06
    RC
    0.06
    pearance
    0.06
    _SK
    0.06
    ){}↵
    0.06
    Activations Density 0.040%

    No Known Activations