© 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. 15-LLAMASCOPE-RES-131K
    6. 103746
    Prev
    Next
    INDEX
    Explanations

    mentions of gratitude and interactions with sponsors or readers

    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
    ahkan
    -0.07
    cket
    -0.07
    ansas
    -0.07
    oni
    -0.06
     Gaz
    -0.06
    é¤
    -0.06
    á»ķ
    -0.06
    oine
    -0.06
    ówn
    -0.06
     Cab
    -0.06
    POSITIVE LOGITS
    ÑįÑĦ
    0.07
    È
    0.07
     direct
    0.06
     DIRECT
    0.06
    gang
    0.06
    &&(
    0.06
    etyl
    0.06
    essen
    0.06
    ɵ
    0.06
    ypass
    0.06
    Activations Density 0.021%

    No Known Activations