© 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. 30232
    Prev
    Next
    INDEX
    Explanations

    elements of commentary or opinion

    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
    meer
    -0.06
    lak
    -0.06
     insignificant
    -0.06
    ving
    -0.06
     ofType
    -0.06
    UBE
    -0.06
    prises
    -0.06
    ãģ«åĩº
    -0.06
    ÑĢ
    -0.06
    sta
    -0.06
    POSITIVE LOGITS
     failed
    0.09
     reality
    0.09
     Failed
    0.09
     Reality
    0.08
     Actual
    0.07
    FAILED
    0.07
    ITHER
    0.07
    .fail
    0.07
    Reality
    0.07
    Unfortunately
    0.07
    Activations Density 0.021%

    No Known Activations