© 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. 15-LLAMASCOPE-RES-131K
    11. 877
    Prev
    Next
    INDEX
    Explanations

    references to algorithms and their evaluations

    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
    upos
    -0.07
    exels
    -0.07
    entine
    -0.07
    eki
    -0.07
     twice
    -0.06
    uta
    -0.06
    oll
    -0.06
    sta
    -0.06
    assi
    -0.06
    155
    -0.06
    POSITIVE LOGITS
     various
    0.07
    ILED
    0.07
     attempts
    0.07
    ãģĭãģĹ
    0.07
    cury
    0.07
    chemes
    0.07
     Attempts
    0.07
     tried
    0.06
     různé
    0.06
    uggestions
    0.06
    Activations Density 0.025%

    No Known Activations