© 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. 12642
    Prev
    Next
    INDEX
    Explanations

    probability calculations

    np_max-act · gemini-2.0-flash

    The neuron consistently lights up on single-letter symbols (like m, d, y, z, etc.) that name outcomes or sequence elements in probability‐of‐sequence math problems.

    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
     horrifying
    -0.07
     predefined
    -0.06
    -power
    -0.06
     attitude
    -0.06
     provisional
    -0.06
    _bn
    -0.06
    ження
    -0.06
    lá
    -0.06
     бит
    -0.06
    -С
    -0.05
    POSITIVE LOGITS
    SignUp
    0.07
    lassen
    0.07
     skept
    0.06
     حالة
    0.06
     건강
    0.06
    redit
    0.06
    _disabled
    0.06
    ième
    0.06
    _drag
    0.06
     nóng
    0.06
    Activations Density 0.005%

    No Known Activations