© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 68364
    Prev
    Next
    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric identifiers (e.g. equation numbers, reference citation numbers, and other decimal‐formatted labels).

    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
    .progressBar
    -0.07
    सर
    -0.07
    .mesh
    -0.07
    _j
    -0.06
     mass
    -0.06
     몽
    -0.06
    ========
    -0.06
    damage
    -0.06
     гер
    -0.06
     PQ
    -0.06
    POSITIVE LOGITS
     регі
    0.06
     испыт
    0.06
     Inf
    0.06
     Nie
    0.06
    (Environment
    0.06
     Hours
    0.06
     pounds
    0.05
    _restart
    0.05
     подум
    0.05
    íše
    0.05
    Activations Density 0.001%

    No Known Activations