© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16816
    Prev
    Next
    INDEX
    Explanations

    terms related to antibiotics and their use

    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
    abouts
    -0.09
    rig
    -0.08
    .Safe
    -0.07
    iola
    -0.07
    kü
    -0.07
    iday
    -0.07
    yer
    -0.07
    illard
    -0.07
    icker
    -0.07
    appy
    -0.07
    POSITIVE LOGITS
    -grade
    0.07
    -rich
    0.07
    pson
    0.07
    elho
    0.06
    empt
    0.06
     sĩ
    0.06
    zept
    0.06
    -free
    0.06
    eros
    0.06
    zed
    0.06
    Activations Density 0.018%

    No Known Activations