© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 75344
    Prev
    Next
    INDEX
    Explanations

    mentions of water quality and related issues

    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
    ibase
    -0.06
    ments
    -0.06
    illard
    -0.06
    umbles
    -0.06
    deen
    -0.06
    pon
    -0.06
    vala
    -0.06
    unei
    -0.06
     injecting
    -0.06
    šek
    -0.06
    POSITIVE LOGITS
    endcode
    0.07
    melon
    0.07
    plode
    0.07
    plx
    0.06
    adors
    0.06
    /feed
    0.06
     Plant
    0.06
    apel
    0.06
    plusplus
    0.06
    _regs
    0.06
    Activations Density 0.022%

    No Known Activations