© 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. 87150
    Prev
    Next
    INDEX
    Explanations

    entries categorized as "Uncategorized."

    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
    .nz
    -0.08
    .scalablytyped
    -0.08
    ÑģоÑĢ
    -0.07
    /sm
    -0.07
    :animated
    -0.06
    edException
    -0.06
    iska
    -0.06
    úi
    -0.06
    wer
    -0.06
    efeller
    -0.06
    POSITIVE LOGITS
    Ùĩ
    0.09
    ETER
    0.07
    itÃł
    0.07
    /un
    0.07
    fir
    0.07
    aed
    0.07
    ahren
    0.07
    eter
    0.07
    lemn
    0.06
    ¤íĶĦ
    0.06
    Activations Density 0.002%

    No Known Activations