© 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. 40697
    Prev
    Next
    INDEX
    Explanations

    conjunctions and phrases that indicate participation or membership

    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
    enson
    -0.07
    annies
    -0.06
    achuset
    -0.06
    ÑĢеб
    -0.06
    igans
    -0.06
    á»įng
    -0.06
    -_
    -0.06
    Intialized
    -0.06
    OptionsResolver
    -0.06
     Lazy
    -0.06
    POSITIVE LOGITS
     finally
    0.12
    finally
    0.10
    Lastly
    0.09
     Lastly
    0.09
     Finally
    0.08
    Finally
    0.08
    ÄĽk
    0.07
    hic
    0.07
    PERT
    0.07
    ãģĿãģ®ä»ĸ
    0.07
    Activations Density 0.046%

    No Known Activations