© 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. 17-LLAMASCOPE-RES-131K
    6. 83165
    Prev
    Next
    INDEX
    Explanations

    terms related to separation and departure

    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
    earing
    -0.09
    pa
    -0.07
     Cob
    -0.07
    980
    -0.07
    itzer
    -0.07
    itters
    -0.07
    ITTER
    -0.07
    gy
    -0.07
    ARING
    -0.06
    rays
    -0.06
    POSITIVE LOGITS
    amento
    0.09
    ments
    0.07
    ools
    0.07
    MENT
    0.07
    icular
    0.07
    ures
    0.07
    mouth
    0.06
    icipation
    0.06
    ullo
    0.06
    .Annotations
    0.06
    Activations Density 0.011%

    No Known Activations