© 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. 56317
    Prev
    Next
    INDEX
    Explanations

    questions related to the context being discussed

    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
    atel
    -0.07
    ÑĮе
    -0.07
    aiser
    -0.07
    alette
    -0.06
    ewis
    -0.06
    егоÑĢ
    -0.06
     iler
    -0.06
    asel
    -0.06
    æĻ¶
    -0.06
    aseline
    -0.06
    POSITIVE LOGITS
    بÙĪاسطة
    0.06
    oj
    0.06
    Ctr
    0.06
    uff
    0.06
    ULK
    0.06
    ANC
    0.06
     Mans
    0.06
    UB
    0.05
     Bucc
    0.05
    855
    0.05
    Activations Density 0.001%

    No Known Activations