© 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. 92546
    Prev
    Next
    INDEX
    Explanations

    key verbs or actions indicating significant events or consequences

    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
     shitty
    -0.07
    alam
    -0.06
    &m
    -0.06
    alat
    -0.06
     Distributed
    -0.06
    adian
    -0.06
    962
    -0.06
    Atlantic
    -0.06
     shit
    -0.06
    zoom
    -0.06
    POSITIVE LOGITS
    _HAVE
    0.06
    ioni
    0.06
    ÃŃme
    0.06
    ngo
    0.06
    ialis
    0.06
    üf
    0.06
    ropa
    0.06
     Burada
    0.06
    æķ¦
    0.06
    anela
    0.06
    Activations Density 0.000%

    No Known Activations