© 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. 78279
    Prev
    Next
    INDEX
    Explanations

    specific components and features related to machinery and industrial processes

    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
    inke
    -0.08
    zdy
    -0.07
    coop
    -0.07
    304
    -0.06
     dy
    -0.06
    èµ·æĿ¥
    -0.06
    illez
    -0.06
    inki
    -0.06
    448
    -0.06
    oton
    -0.06
    POSITIVE LOGITS
    -focused
    0.08
    eyim
    0.07
    geh
    0.07
     ìłĦìļ©
    0.07
    .setFocus
    0.07
    pecific
    0.07
    -specific
    0.07
    /package
    0.07
    å°Ī
    0.06
    ÏĦοκ
    0.06
    Activations Density 0.049%

    No Known Activations