© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 44522
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    This neuron fires on LaTeX‐style mathematical content (e.g. “\sum,” “\frac,” superscripts/subscripts, and variable‐or number tokens inside math).

    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
     �
    -0.06
    こう
    -0.06
    }.${
    -0.06
    awning
    -0.06
     Fluid
    -0.06
     Had
    -0.06
    domains
    -0.05
     nêu
    -0.05
     Sala
    -0.05
     belum
    -0.05
    POSITIVE LOGITS
    五月
    0.07
     ',',
    0.07
     Αθή
    0.06
     Респ
    0.06
    ��
    0.06
     traj
    0.06
    HE
    0.06
    .HORIZONTAL
    0.06
     halfway
    0.06
     gratuites
    0.06
    Activations Density 0.017%

    No Known Activations