© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 7790
    Prev
    Next
    INDEX
    Explanations

    td

    np_max-act · gemini-2.0-flash

    The neuron consistently activates on the substring “mtd,” e.g. in file paths or identifiers (like “/mtd/…” or “mtd” tokens).

    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
    etime
    -0.06
     UNIX
    -0.06
    /map
    -0.06
     Accom
    -0.06
     ประเทศ
    -0.06
     �
    -0.06
     сог
    -0.06
    ante
    -0.06
    ngrx
    -0.06
    istributions
    -0.06
    POSITIVE LOGITS
    -exclusive
    0.07
    udget
    0.07
     Authors
    0.06
     prostit
    0.06
    ічного
    0.06
    ード
    0.06
    Ed
    0.06
     شدند
    0.06
    Secret
    0.06
     health
    0.06
    Activations Density 0.008%

    No Known Activations