© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 75317
    Prev
    Next
    INDEX
    Explanations

    references to competition or entry into markets or events

    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
     Grat
    -0.07
    é¼
    -0.07
    uger
    -0.07
    /private
    -0.06
    unami
    -0.06
    esian
    -0.06
     Platz
    -0.06
    imeters
    -0.05
     Reb
    -0.05
     Ear
    -0.05
    POSITIVE LOGITS
    ils
    0.08
    sse
    0.07
    ordin
    0.07
     thẳng
    0.07
    utar
    0.07
    angler
    0.07
    ONO
    0.07
    prises
    0.07
    asse
    0.07
    shot
    0.07
    Activations Density 0.002%

    No Known Activations