© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 82610
    Prev
    Next
    INDEX
    Explanations

    instances of the word "show" and its various forms in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isper
    -0.07
    ī
    -0.06
    endor
    -0.06
    AtPath
    -0.06
     Schiff
    -0.06
    zig
    -0.06
    HCI
    -0.06
    nis
    -0.06
    éĻ
    -0.06
    (Yii
    -0.06
    POSITIVE LOGITS
    rooms
    0.08
    piece
    0.07
    boat
    0.07
    manship
    0.07
     Signs
    0.07
     signs
    0.07
    biz
    0.06
    еÑĢеж
    0.06
    683
    0.06
    izr
    0.06
    Activations Density 0.018%

    No Known Activations