© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 17926
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, entities, or groups in the context of relationships and decision-making

    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
    Obsolete
    -0.07
    campo
    -0.07
    obo
    -0.07
    alis
    -0.07
    nim
    -0.07
    izzie
    -0.07
    usta
    -0.07
     воÑĤ
    -0.07
    edio
    -0.07
    огÑĥ
    -0.06
    POSITIVE LOGITS
     likely
    0.10
     could
    0.10
     already
    0.10
     probably
    0.10
     might
    0.10
    umably
    0.08
     may
    0.08
    likely
    0.08
     possibly
    0.08
     unlikely
    0.08
    Activations Density 0.042%

    No Known Activations