© 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. 17-LLAMASCOPE-RES-131K
    11. 3899
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and their relationships, particularly with respect to contrasts and depth of meaning

    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
     nejen
    -0.09
     asÃŃ
    -0.08
    rowsable
    -0.07
     oraz
    -0.07
     thus
    -0.07
     ainsi
    -0.07
    -urlencoded
    -0.07
     именно
    -0.07
     kromÄĽ
    -0.07
     gratuite
    -0.07
    POSITIVE LOGITS
     depending
    0.14
    depending
    0.12
     whichever
    0.11
     if
    0.09
     depends
    0.09
    depends
    0.08
     Depends
    0.08
    ichever
    0.08
     tùy
    0.08
     завиÑģиÑĤ
    0.07
    Activations Density 0.065%

    No Known Activations