© 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. 70135
    Prev
    Next
    INDEX
    Explanations

    references to situations or conditions surrounding specific events

    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
    ãģĦãĤĭ
    -0.08
    abbit
    -0.08
    thing
    -0.08
    ery
    -0.07
    tered
    -0.07
    terra
    -0.07
    izard
    -0.07
    ore
    -0.07
    ard
    -0.06
    term
    -0.06
    POSITIVE LOGITS
     circumstances
    0.13
     circumstance
    0.10
     conditions
    0.09
    ums
    0.08
    itious
    0.08
    conditions
    0.08
    uits
    0.08
     situations
    0.07
    conds
    0.07
     surrounding
    0.07
    Activations Density 0.006%

    No Known Activations