© 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. 55794
    Prev
    Next
    INDEX
    Explanations

    references to computer system specifications and parameters

    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
    hdl
    -0.07
     ekip
    -0.07
    rys
    -0.07
    yat
    -0.07
    eyse
    -0.07
     naopak
    -0.07
    ıb
    -0.07
    ubat
    -0.07
    holm
    -0.07
    lore
    -0.06
    POSITIVE LOGITS
     =
    0.12
    =
    0.08
     times
    0.06
     TIMES
    0.06
     equals
    0.06
     Result
    0.06
     vezes
    0.06
    xis
    0.06
    座
    0.06
     =↵
    0.06
    Activations Density 0.036%

    No Known Activations