© 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. 89638
    Prev
    Next
    INDEX
    Explanations

    business growth and size

    np_max-act · gemini-2.0-flash

    This neuron activates on language describing scalability and capacity—words and phrases like “scalable,” “can support,” “large-scale,” etc.

    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
     dac
    -0.07
     Barry
    -0.06
     copied
    -0.06
    FAST
    -0.06
     titled
    -0.06
     fast
    -0.06
    ."'";↵
    -0.06
    utorial
    -0.06
    /latest
    -0.06
    actoring
    -0.06
    POSITIVE LOGITS
    减
    0.07
    _An
    0.06
     FontAwesome
    0.06
     tenga
    0.06
    ibbon
    0.06
     cé
    0.06
    _SIGNAL
    0.06
    _Off
    0.06
     sistemi
    0.06
    $template
    0.06
    Activations Density 0.047%

    No Known Activations