© 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. 61880
    Prev
    Next
    INDEX
    Explanations

    terms related to antibiotics and their effects or usage

    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
    ibi
    -0.07
    ledon
    -0.06
     shell
    -0.06
    edith
    -0.06
    erset
    -0.06
    quet
    -0.06
     knot
    -0.06
    uant
    -0.06
     stump
    -0.06
    dbh
    -0.06
    POSITIVE LOGITS
    isl
    0.08
    Ctrls
    0.07
    ìĬ¤ì½Ķ
    0.07
    _OPTS
    0.07
    OwnProperty
    0.07
    ÑĤаж
    0.07
     Patterson
    0.07
    ÏĩÏİ
    0.07
    polator
    0.07
    _typeof
    0.06
    Activations Density 0.000%

    No Known Activations