© 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. 5-LLAMASCOPE-RES-131K
    11. 126430
    Prev
    Next
    INDEX
    Explanations

    instances of the article "the."

    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
    asaki
    -0.09
    _funcs
    -0.06
    üçük
    -0.06
    /port
    -0.06
    rak
    -0.06
    amı
    -0.06
    nore
    -0.06
    ?action
    -0.06
    treeview
    -0.06
    ling
    -0.06
    POSITIVE LOGITS
    onomy
    0.07
    jez
    0.06
    &E
    0.06
    OMP
    0.06
    engeance
    0.06
    THON
    0.06
    IVO
    0.06
    ARI
    0.06
    855
    0.06
    485
    0.06
    Activations Density 0.085%

    No Known Activations