© 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. 39393
    Prev
    Next
    INDEX
    Explanations

    terms related to gaming and technology features

    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
    839
    -0.06
    ocuk
    -0.06
    Ìģt
    -0.05
     least
    -0.05
    à¹Ħà¸Ĥ
    -0.05
    ردÙĩ
    -0.05
    ::
    -0.05
    mek
    -0.05
     Clayton
    -0.05
     corpor
    -0.05
    POSITIVE LOGITS
    _sessions
    0.07
    rust
    0.07
    "]=="
    0.07
    esco
    0.07
    ystate
    0.07
    OnInit
    0.07
    Shock
    0.07
    ropol
    0.07
    CTR
    0.07
    sessions
    0.07
    Activations Density 0.000%

    No Known Activations