© 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. 15-LLAMASCOPE-RES-131K
    6. 26868
    Prev
    Next
    INDEX
    Explanations

    mentions of new online resources or publications

    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
     
    -0.07
     maker
    -0.06
     abs
    -0.06
     makers
    -0.05
     d
    -0.05
     a
    -0.05
     pals
    -0.05
     h
    -0.05
     cold
    -0.05
     an
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.09
    vailability
    0.09
    CRET
    0.09
     {?>↵
    0.09
    گاب
    0.09
    .foundation
    0.09
    ilden
    0.09
    .ย
    0.09
    _HINT
    0.08
    -NLS
    0.08
    Activations Density 0.002%

    No Known Activations