© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 88504
    Prev
    Next
    INDEX
    Explanations

    references to importance or significance regarding a subject or character

    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
    assin
    -0.07
    ema
    -0.07
    oug
    -0.06
    aiser
    -0.06
    readcr
    -0.06
     resultMap
    -0.06
     buurt
    -0.06
     likely
    -0.06
    ç§ĭ
    -0.06
    alus
    -0.06
    POSITIVE LOGITS
    habi
    0.07
    ogenic
    0.06
    angler
    0.06
    jec
    0.06
    utzer
    0.06
    157
    0.06
    åıĸãĤĬ
    0.06
    trand
    0.06
    clipse
    0.06
    exo
    0.06
    Activations Density 0.000%

    No Known Activations