© 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. 30826
    Prev
    Next
    INDEX
    Explanations

    rail

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the string “rail” (e.g. in “Rail,” “Railway,” “Railroad,” “Rails-to-Trails,” etc.).

    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
     voluntarily
    -0.08
     syndrome
    -0.07
     Syndrome
    -0.07
    adj
    -0.07
     Clo
    -0.07
     zboží
    -0.07
     exporters
    -0.07
     Kitty
    -0.07
    worthy
    -0.07
    IVER
    -0.07
    POSITIVE LOGITS
     rail
    0.14
     Rail
    0.14
    ail
    0.10
     rails
    0.10
    Rail
    0.10
     sail
    0.09
     Sail
    0.09
    rail
    0.08
     railing
    0.08
    rails
    0.08
    Activations Density 0.005%

    No Known Activations