© 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. 54166
    Prev
    Next
    INDEX
    Explanations

    references to the need for increased effort or improvement in various contexts

    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
    ensch
    -0.07
    utsch
    -0.06
    ió
    -0.06
     èª
    -0.06
    _wind
    -0.06
    ayi
    -0.06
    acco
    -0.06
    rees
    -0.06
    oi
    -0.05
    erna
    -0.05
    POSITIVE LOGITS
    yt
    0.07
    ibly
    0.07
     than
    0.07
    ible
    0.07
    utenberg
    0.07
    oningen
    0.07
    than
    0.07
    eyond
    0.06
    ymi
    0.06
    COME
    0.06
    Activations Density 0.029%

    No Known Activations