© 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. 98021
    Prev
    Next
    INDEX
    Explanations

    elements related to scientific studies and gene references

    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
    estre
    -0.08
    geries
    -0.08
    GetMethod
    -0.08
    throp
    -0.07
    té
    -0.07
    омÑĸ
    -0.07
    ç¦ıåĪ©
    -0.07
    ë»
    -0.07
     lã
    -0.07
    .Apis
    -0.07
    POSITIVE LOGITS
    emann
    0.07
    Assembly
    0.06
    Abs
    0.06
     punct
    0.06
     Ñģил
    0.06
     pulse
    0.06
     Pulse
    0.06
    atica
    0.06
     Abbott
    0.05
     tet
    0.05
    Activations Density 0.123%

    No Known Activations