© 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. 107426
    Prev
    Next
    INDEX
    Explanations

    concepts related to programming templates and specialization

    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
    -valu
    -0.07
    èĦ
    -0.07
    modifiable
    -0.07
    vé
    -0.07
    opard
    -0.06
    iev
    -0.06
    avel
    -0.06
    urre
    -0.06
    ulas
    -0.06
    Getter
    -0.06
    POSITIVE LOGITS
     versions
    0.06
    çīĪæľ¬
    0.06
     vyh
    0.06
     conflicts
    0.06
     version
    0.06
     pornos
    0.06
     Versions
    0.06
     hi
    0.06
    LEC
    0.06
     Edison
    0.06
    Activations Density 0.004%

    No Known Activations