© 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. 15-RESID-POST-AA
    11. 115124
    Prev
    Next
    INDEX
    Explanations

    sentences or passages containing technical, scientific, or domain-specific discussion (formal/academic/technical writing).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acidad
    -0.06
     traits
    -0.06
    _counters
    -0.06
     думку
    -0.06
     PRIVATE
    -0.06
     mascul
    -0.06
    Дата
    -0.05
    ağa
    -0.05
     ман
    -0.05
     mocks
    -0.05
    POSITIVE LOGITS
    }@
    0.07
    انت
    0.07
    "T
    0.07
     [↵↵
    0.07
    职
    0.06
    ('|
    0.06
     Iowa
    0.06
     lavender
    0.06
    รณ
    0.06
    izu
    0.06
    Activations Density 0.000%

    No Known Activations