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. 91275
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    This neuron activates on floating-point numeric tokens (numbers containing a decimal point).

    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
     getMessage
    -0.07
    ANGUAGE
    -0.07
    Mod
    -0.07
     Ra
    -0.06
    Informe
    -0.06
    ONUS
    -0.06
    بوب
    -0.06
    wipe
    -0.06
     "<<
    -0.06
    <|eot_id|>
    -0.06
    POSITIVE LOGITS
    				↵
    0.07
     multiplying
    0.07
     intelligence
    0.06
     omnip
    0.06
    (cb
    0.06
     spotlight
    0.06
     callbacks
    0.06
    Dia
    0.06
     anch
    0.06
    .Stage
    0.06
    Activations Density 0.005%

    No Known Activations