© 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. 39150
    Prev
    Next
    INDEX
    Explanations

    phrases related to improvement or enhancement

    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
    енз
    -0.07
    ảo
    -0.07
    ONSE
    -0.07
    оÑĢд
    -0.07
    è´£
    -0.07
    دÙĪ
    -0.07
    ÙĤÛĮ
    -0.07
    isl
    -0.06
     duy
    -0.06
    doors
    -0.06
    POSITIVE LOGITS
     overall
    0.09
     quality
    0.09
     chances
    0.08
    -quality
    0.08
     odds
    0.08
     understanding
    0.07
     lives
    0.07
    overall
    0.07
     upon
    0.07
     Odds
    0.07
    Activations Density 0.022%

    No Known Activations