© 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. 79873
    Prev
    Next
    INDEX
    Explanations

    references to quantities or the word "some" in various contexts

    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
    zon
    -0.07
    roperty
    -0.07
    zens
    -0.07
    onium
    -0.07
    strup
    -0.07
    izza
    -0.07
    tmpl
    -0.07
    wart
    -0.07
    anning
    -0.07
    /INFO
    -0.07
    POSITIVE LOGITS
     cases
    0.09
     instances
    0.07
     case
    0.07
     caso
    0.07
     casos
    0.07
    cases
    0.06
     instance
    0.06
    ,
    0.06
     places
    0.06
    iah
    0.06
    Activations Density 0.016%

    No Known Activations