© 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 EvalsExportsAPI 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. 106520
    Prev
    Next
    INDEX
    Explanations

    mentions of educational grade levels

    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
    ļ
    -0.07
    ©
    -0.07
    ecided
    -0.07
    aise
    -0.07
    ym
    -0.06
    maf
    -0.06
    loha
    -0.06
    riet
    -0.06
    033
    -0.06
    vailability
    -0.06
    POSITIVE LOGITS
    -level
    0.07
    enko
    0.07
     Cop
    0.07
    -long
    0.07
    ë³Ħ
    0.07
    оваÑĢи
    0.07
    IENT
    0.07
    -specific
    0.06
    اØŃÛĮ
    0.06
    .experimental
    0.06
    Activations Density 0.002%

    No Known Activations