© 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. 84527
    Prev
    Next
    INDEX
    Explanations

    statements or claims that provide factual confirmation or evidence

    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
    -navbar
    -0.07
    اÙĨد
    -0.07
    awi
    -0.07
    è¬
    -0.07
    itol
    -0.07
    oug
    -0.07
     forb
    -0.07
    اشت
    -0.06
    sted
    -0.06
    oger
    -0.06
    POSITIVE LOGITS
     fact
    0.11
     FACT
    0.09
     Fact
    0.09
    fact
    0.08
     ÑĦакÑĤ
    0.07
    Fact
    0.07
     facts
    0.07
     true
    0.07
    ackbar
    0.07
     truth
    0.07
    Activations Density 0.052%

    No Known Activations