© 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. 29502
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the importance of drawing from various sources of expertise and literature in different contexts

    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
    empo
    -0.08
     {{{
    -0.07
    YK
    -0.07
    zw
    -0.07
    tout
    -0.06
    AGR
    -0.06
     MatSnackBar
    -0.06
    jong
    -0.06
    менно
    -0.06
    RSS
    -0.06
    POSITIVE LOGITS
     resources
    0.12
     experiences
    0.10
     sources
    0.09
     reserves
    0.09
     reservoir
    0.09
     experience
    0.09
    -resources
    0.09
     reserve
    0.08
     pool
    0.08
    resources
    0.08
    Activations Density 0.012%

    No Known Activations