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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 91782
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens containing decimal points (i.e. floating-point/statistical values).

    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
     Cout
    -0.07
     pruning
    -0.06
     �
    -0.06
    962
    -0.06
     histoire
    -0.06
     grated
    -0.06
     geopol
    -0.06
     �
    -0.06
     �
    -0.06
    <ActionResult
    -0.06
    POSITIVE LOGITS
     oath
    0.08
    irtschaft
    0.08
    _skb
    0.07
    َو
    0.07
     "('
    0.07
    __((
    0.06
    oč
    0.06
     düğ
    0.06
    처
    0.06
    stashop
    0.06
    Activations Density 0.033%

    No Known Activations