© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 110318
    Prev
    Next
    INDEX
    Explanations

    G

    np_max-act · gemini-2.0-flash

    This neuron detects section‐heading text in scientific documents (e.g. numbered titles like “2. Structure of Human Brain Gangliosides”).

    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
    Enumeration
    -0.06
     Plymouth
    -0.06
     информ
    -0.06
     FACT
    -0.06
    _EXIST
    -0.06
    pathname
    -0.06
     moż
    -0.06
    ()]↵↵
    -0.06
     депут
    -0.06
     Их
    -0.06
    POSITIVE LOGITS
     joints
    0.07
    stered
    0.07
    [word
    0.07
     Odds
    0.07
    Drink
    0.07
     cenu
    0.06
    &page
    0.06
     hardship
    0.06
    	const
    0.06
     *_
    0.06
    Activations Density 0.025%

    No Known Activations