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. 85258
    Prev
    Next
    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash

    mathematical expressions involving derivatives.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on numeric literals (especially floating‐point numbers, often shown in parentheses).

    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
    少年
    -0.07
    sing
    -0.07
    Pal
    -0.07
     ArrayAdapter
    -0.06
     destac
    -0.06
    一年
    -0.06
    *d
    -0.06
    Ten
    -0.06
     nickel
    -0.06
    gateway
    -0.06
    POSITIVE LOGITS
    	Token
    0.07
    uble
    0.07
     อำ
    0.07
     скры
    0.06
    ⌒
    0.06
     uncont
    0.06
     Merkezi
    0.06
    -graph
    0.06
    _serialize
    0.06
    locking
    0.06
    Activations Density 0.007%

    No Known Activations