© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 13484
    Prev
    Next
    INDEX
    Explanations

    Dishes

    np_max-act · gemini-2.0-flash

    The neuron is detecting mentions of specific dish names (i.e. the titles of individual food items).

    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
     pulse
    -0.07
    (text
    -0.07
     influx
    -0.07
    _WIDTH
    -0.07
    とう
    -0.06
    erce
    -0.06
    _dot
    -0.06
    	font
    -0.06
    を見
    -0.06
     Pur
    -0.06
    POSITIVE LOGITS
    .setCancelable
    0.07
     звичай
    0.07
    터
    0.06
    }))↵↵
    0.06
    memiş
    0.06
    “↵↵
    0.06
    sect
    0.06
    均
    0.06
     edilen
    0.06
    保障
    0.06
    Activations Density 0.069%

    No Known Activations