© 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. 15-LLAMASCOPE-RES-131K
    11. 87488
    Prev
    Next
    INDEX
    Explanations

    the use of the word "that" 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
    çĭIJ
    -0.08
    irs
    -0.06
    aga
    -0.06
    iras
    -0.06
    moz
    -0.06
    _Blue
    -0.06
    ria
    -0.06
    asm
    -0.06
    PA
    -0.06
     Cel
    -0.06
    POSITIVE LOGITS
    ivre
    0.08
     Barg
    0.07
    nock
    0.06
    alach
    0.06
    ãĤ¢ãĥ¼
    0.06
    оÑĤÑĢеб
    0.06
    /goto
    0.06
    092
    0.06
    ози
    0.06
    ξε
    0.06
    Activations Density 0.016%

    No Known Activations