© 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. 87351
    Prev
    Next
    INDEX
    Explanations

    references to specific numerical values or related terms in a technical context

    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
    /loose
    -0.07
    axed
    -0.07
    stantiate
    -0.06
    \grid
    -0.06
    adele
    -0.06
    enek
    -0.06
    itted
    -0.06
    ês
    -0.06
    ati
    -0.06
    $MESS
    -0.06
    POSITIVE LOGITS
    ÙĭØĮ
    0.08
    chap
    0.07
    leton
    0.07
     forc
    0.07
    Ùĭ
    0.07
    -)
    0.07
    acades
    0.06
    OTE
    0.06
    oras
    0.06
    çŃij
    0.06
    Activations Density 0.009%

    No Known Activations