© 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. 92907
    Prev
    Next
    INDEX
    Explanations

    words indicating strong commitment or focus towards a subject

    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
    el
    -0.07
    è«
    -0.06
    _TRACE
    -0.06
    ere
    -0.06
    blob
    -0.06
     Todd
    -0.06
    aci
    -0.06
    LM
    -0.06
    emoc
    -0.06
    ech
    -0.05
    POSITIVE LOGITS
    beros
    0.07
    oda
    0.07
    adoo
    0.07
    marshal
    0.07
    ırak
    0.07
    warf
    0.07
    utton
    0.07
    æĶ
    0.07
    Probe
    0.06
    /pdf
    0.06
    Activations Density 0.006%

    No Known Activations