© 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. 30714
    Prev
    Next
    INDEX
    Explanations

    references to the term "tetra," particularly in a scientific or chemical context

    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
    erli
    -0.08
    osate
    -0.08
     maduras
    -0.08
    iá»ĥm
    -0.07
    itar
    -0.07
    ofday
    -0.07
    izont
    -0.07
    기ëıĦ
    -0.07
    orget
    -0.07
    ngör
    -0.07
    POSITIVE LOGITS
    uo
    0.08
    aver
    0.07
    ĭ
    0.06
    odor
    0.06
    ischer
    0.06
     Tet
    0.06
    ht
    0.06
    gem
    0.06
    ty
    0.06
    ef
    0.06
    Activations Density 0.003%

    No Known Activations