© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 90405
    Prev
    Next
    INDEX
    Explanations

    terms related to separation and disconnection

    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
    eum
    -0.07
    ancode
    -0.07
    bÄĽh
    -0.07
    lek
    -0.07
    liche
    -0.07
    lichen
    -0.06
     Scha
    -0.06
    oga
    -0.06
    ICODE
    -0.06
    roe
    -0.06
    POSITIVE LOGITS
     بÙĨدÛĮ
    0.07
    eras
    0.07
     compartments
    0.07
    ted
    0.07
    PLICATE
    0.07
    ToOne
    0.07
    SSIP
    0.07
    individual
    0.06
    šek
    0.06
    ed
    0.06
    Activations Density 0.006%

    No Known Activations