Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 93049
    Prev
    Next
    INDEX
    Explanations

    code and symbols

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on chemical compound names—especially polymer or “Poly-” prefixed terms—while ignoring ordinary words.

    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
    �
    -0.07
     spies
    -0.07
    Map
    -0.07
    	ctx
    -0.06
    Sum
    -0.06
    _human
    -0.06
    شتر
    -0.06
     тощо
    -0.06
     surpr
    -0.06
    incorrect
    -0.06
    POSITIVE LOGITS
    )}}
    0.07
    (port
    0.07
     competent
    0.07
     waved
    0.07
    ısına
    0.06
     Zhou
    0.06
    орон
    0.06
     phá
    0.06
     populace
    0.06
    .Concurrent
    0.06
    Activations Density 0.140%

    No Known Activations