© 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. 125965
    Prev
    Next
    INDEX
    Explanations

    terms related to synergy and concepts of blending or combining elements

    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
    itto
    -0.08
    legg
    -0.07
    /Graphics
    -0.07
    ucc
    -0.07
    quo
    -0.07
    ame
    -0.07
    arena
    -0.07
    лег
    -0.07
    arend
    -0.06
    rats
    -0.06
    POSITIVE LOGITS
    ously
    0.10
    dney
    0.07
    ically
    0.07
     effects
    0.07
    829
    0.06
    ences
    0.06
    UIL
    0.06
    Rnd
    0.06
    .absolute
    0.06
    ently
    0.06
    Activations Density 0.002%

    No Known Activations