© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 68843
    Prev
    Next
    INDEX
    Explanations

    error

    np_max-act · gemini-2.0-flash

    This neuron detects numeric mentions of error estimates or tolerances (i.e. values quantifying “error” in computations).

    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
    	Init
    -0.07
    Functions
    -0.06
    消息
    -0.06
     наслед
    -0.06
     *****
    -0.06
     Appearance
    -0.06
     panor
    -0.06
     xmin
    -0.06
    _func
    -0.06
     Function
    -0.06
    POSITIVE LOGITS
     Eli
    0.06
    ارب
    0.06
    च
    0.06
    CSR
    0.06
    ch
    0.06
    828
    0.06
     Midnight
    0.06
    etary
    0.06
    verse
    0.06
    ר
    0.06
    Activations Density 0.009%

    No Known Activations