© 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. 18319
    Prev
    Next
    INDEX
    Explanations

    terms related to calcium and its presence 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
    laps
    -0.08
    lez
    -0.07
    lis
    -0.07
    gi
    -0.07
    ilis
    -0.07
    lane
    -0.07
    rans
    -0.07
    lene
    -0.06
    ppard
    -0.06
    uil
    -0.06
    POSITIVE LOGITS
    /cal
    0.08
    -rich
    0.07
    esium
    0.07
    ifornia
    0.07
     carbonate
    0.07
    orus
    0.07
     deficiency
    0.07
    NDAR
    0.07
    ews
    0.06
    zac
    0.06
    Activations Density 0.002%

    No Known Activations