© 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. 61193
    Prev
    Next
    INDEX
    Explanations

    the word "such" as a marker to introduce examples or specifics

    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
    ascal
    -0.09
    ollo
    -0.08
    acin
    -0.08
    Å¡k
    -0.07
    lio
    -0.07
    ouro
    -0.07
    aceous
    -0.07
    iesel
    -0.07
    ital
    -0.07
    imax
    -0.07
    POSITIVE LOGITS
    esin
    0.07
     обÑĢазом
    0.07
    likle
    0.07
    like
    0.07
    es
    0.07
    s
    0.07
     as
    0.07
    erb
    0.06
    er
    0.06
     an
    0.06
    Activations Density 0.029%

    No Known Activations