© 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. 61987
    Prev
    Next
    INDEX
    Explanations

    various significant punctuation marks and common conjunctions related to context and structure

    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
    .nasa
    -0.08
    .setVertical
    -0.08
    ameda
    -0.08
    mey
    -0.08
    atha
    -0.08
    LayoutConstraint
    -0.08
    omat
    -0.08
    alama
    -0.08
    apsible
    -0.08
    Å¡e
    -0.08
    POSITIVE LOGITS
     Brent
    0.06
     David
    0.06
     Jim
    0.06
     Import
    0.06
     President
    0.05
     sources
    0.05
     Mike
    0.05
     nor
    0.05
     consensus
    0.05
     As
    0.05
    Activations Density 0.019%

    No Known Activations