© 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. 4552
    Prev
    Next
    INDEX
    Explanations

    variations of the word "tot," likely looking for references to quantities or counts

    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
    edImage
    -0.08
    à¤¿à¤Ľ
    -0.07
    osate
    -0.07
    ῦ
    -0.07
    ãĥĥãĥģ
    -0.07
    apphire
    -0.07
    oS
    -0.07
    eil
    -0.07
    alon
    -0.07
    ozilla
    -0.07
    POSITIVE LOGITS
    ally
    0.09
    ALLY
    0.07
    ius
    0.07
    anch
    0.07
    ANCH
    0.07
     Bentley
    0.07
    u
    0.06
    ted
    0.06
    te
    0.06
    tn
    0.06
    Activations Density 0.014%

    No Known Activations