© 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. 15-LLAMASCOPE-RES-131K
    11. 61996
    Prev
    Next
    INDEX
    Explanations

    numerical data and specific values in scientific contexts

    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
    iska
    -0.07
    éc
    -0.07
    icode
    -0.06
    OKIE
    -0.06
     friction
    -0.06
    mek
    -0.06
    izm
    -0.06
    avec
    -0.06
     mnemonic
    -0.06
    otch
    -0.06
    POSITIVE LOGITS
    afd
    0.06
     Ark
    0.06
     QFile
    0.06
     dil
    0.06
    .scalablytyped
    0.06
    inion
    0.06
    /Home
    0.06
     Dil
    0.06
     جاÙĨ
    0.06
     Serg
    0.05
    Activations Density 0.002%

    No Known Activations