© 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. 126403
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Sp" or similar variations that signify a specific focus on certain terms or topics

    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
    ameda
    -0.09
    iversal
    -0.08
    bsolute
    -0.07
    óc
    -0.07
    maids
    -0.07
     stát
    -0.07
    brush
    -0.07
    ampire
    -0.07
    utilus
    -0.07
    imitive
    -0.07
    POSITIVE LOGITS
    ase
    0.06
     Atkins
    0.06
    illo
    0.06
    ren
    0.06
    iga
    0.06
    -eye
    0.06
    shire
    0.06
     usual
    0.06
     Farr
    0.06
     org
    0.06
    Activations Density 0.027%

    No Known Activations