© 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. 76337
    Prev
    Next
    INDEX
    Explanations

    references to specific documents, events, or instances in historical context

    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
    chw
    -0.08
    .desc
    -0.07
    amiliar
    -0.07
     Pul
    -0.07
    ouv
    -0.07
    oggler
    -0.07
    conde
    -0.07
    .Mask
    -0.07
    ouncements
    -0.06
     suy
    -0.06
    POSITIVE LOGITS
     matter
    0.07
    oret
    0.07
     hereby
    0.07
     pec
    0.06
    åĶ®
    0.06
    matter
    0.05
    itol
    0.05
    oretical
    0.05
     decision
    0.05
    agal
    0.05
    Activations Density 0.036%

    No Known Activations