© 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. 2091
    Prev
    Next
    INDEX
    Explanations

    instances of general statements about experiences or observations

    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
    omik
    -0.07
    éĤª
    -0.06
    istributed
    -0.06
    ENDED
    -0.06
    utos
    -0.06
    amin
    -0.06
    åĹ
    -0.06
    ãĥķãĤ
    -0.06
    quared
    -0.06
    SYNC
    -0.06
    POSITIVE LOGITS
    oom
    0.06
    mos
    0.06
     Plus
    0.06
    temps
    0.06
    İ·
    0.06
    ãĥ³ãĥIJ
    0.06
    stru
    0.06
    imes
    0.06
    á»±
    0.05
    kees
    0.05
    Activations Density 0.007%

    No Known Activations