© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 95092
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and individuals involved in lawsuits

    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
    MUX
    -0.07
    nett
    -0.07
    tement
    -0.07
    ppv
    -0.07
    VERS
    -0.07
    оÑģÑĤ
    -0.06
    enheim
    -0.06
    gages
    -0.06
    оÑĢоÑĤ
    -0.06
    ãĤ¤ãĥ«
    -0.06
    POSITIVE LOGITS
    urf
    0.06
     Guaranteed
    0.06
    alias
    0.05
    lip
    0.05
     Efficient
    0.05
    üzel
    0.05
    rons
    0.05
    uing
    0.05
    rai
    0.05
    rian
    0.05
    Activations Density 0.021%

    No Known Activations