© 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. 9-LLAMASCOPE-RES-131K
    11. 97918
    Prev
    Next
    INDEX
    Explanations

    terms and values associated with complex mathematical or programming constructs

    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
     kli
    -0.07
    Near
    -0.07
    CAN
    -0.06
     Snyder
    -0.06
    klä
    -0.06
    upa
    -0.06
    ono
    -0.06
    chunk
    -0.06
     skeleton
    -0.06
    APH
    -0.06
    POSITIVE LOGITS
    öst
    0.07
    arme
    0.07
    oS
    0.06
    skins
    0.06
    qv
    0.06
    arness
    0.06
    олж
    0.06
    	TokenName
    0.06
    ogui
    0.06
    fk
    0.06
    Activations Density 0.131%

    No Known Activations