Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 77228
    Prev
    Next
    INDEX
    Explanations

    references to leadership and innovation within various fields and sectors

    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
    nem
    -0.07
    atch
    -0.06
     yine
    -0.06
     Wie
    -0.06
    ausal
    -0.06
     Lux
    -0.06
    å¾ħ
    -0.06
    gid
    -0.06
    /people
    -0.06
    eki
    -0.06
    POSITIVE LOGITS
    lius
    0.06
    APT
    0.06
    __/
    0.06
    mmc
    0.06
     efforts
    0.06
    ehir
    0.06
    iesen
    0.06
    ipay
    0.06
    isbury
    0.06
    voir
    0.06
    Activations Density 0.016%

    No Known Activations