© 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. 7173
    Prev
    Next
    INDEX
    Explanations

    For

    np_max-act · gemini-2.0-flash

    This neuron detects the word “For” when it introduces example or explanatory phrases (e.g., “For example,” “For more details,” “For the bone marrow…”).

    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
     less
    -0.08
    .vis
    -0.07
    لمه
    -0.07
     Sé
    -0.07
     injuries
    -0.07
    消
    -0.07
    rylic
    -0.06
     Cube
    -0.06
     nano
    -0.06
     me
    -0.06
    POSITIVE LOGITS
     For
    0.13
    For
    0.12
    (for
    0.10
    “For
    0.10
    —for
    0.10
    .For
    0.10
    "For
    0.10
     FOR
    0.09
     for
    0.09
    #for
    0.08
    Activations Density 0.049%

    No Known Activations