© 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
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 23204
    Prev
    Next
    INDEX
    Explanations

    intent

    np_max-act · gemini-2.0-flash

    mentions of "intent" or intent-detection/intent-based routing in conversational systems.

    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
     тради
    -0.07
     kaz
    -0.06
    azole
    -0.06
    Marg
    -0.06
     Zoo
    -0.06
    ampton
    -0.06
     zg
    -0.06
    cob
    -0.06
    ладу
    -0.06
    EXAMPLE
    -0.06
    POSITIVE LOGITS
     intent
    0.12
     Intent
    0.11
    intent
    0.09
    mt
    0.08
    (ignore
    0.08
     odds
    0.08
    -after
    0.08
     matter
    0.07
    Enum
    0.07
    /react
    0.07
    Activations Density 0.006%

    No Known Activations