© 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
    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. 12713
    Prev
    Next
    INDEX
    Explanations

    approximate numbers

    np_max-act · gemini-2.0-flash

    The neuron fires on approximate‐quantity markers in number expressions (e.g. “odd,” “plus,” “or so”).

    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
     جهانی
    -0.07
    _NE
    -0.07
     colonies
    -0.06
    �
    -0.06
    주는
    -0.06
    false
    -0.06
     reconstruction
    -0.06
    概
    -0.06
     روشن
    -0.06
     음악
    -0.06
    POSITIVE LOGITS
    bsd
    0.07
    roll
    0.07
     Allow
    0.07
    *a
    0.07
     Busy
    0.06
    )?;↵↵
    0.06
    osl
    0.06
    ifiable
    0.06
     trình
    0.06
    투
    0.06
    Activations Density 0.008%

    No Known Activations