© 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. 80253
    Prev
    Next
    INDEX
    Explanations

    information related to essential knowledge or awareness

    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
    ior
    -0.06
    ucht
    -0.06
    ity
    -0.06
    OLLOW
    -0.06
    elden
    -0.06
    _exe
    -0.06
     Ernst
    -0.06
    awan
    -0.05
    monic
    -0.05
    ensen
    -0.05
    POSITIVE LOGITS
    OffsetTable
    0.09
     about
    0.09
    gnore
    0.08
    about
    0.08
    ozem
    0.08
    -about
    0.08
    ledged
    0.07
     ìĤ¬íķŃ
    0.07
    eil
    0.07
    "struct
    0.07
    Activations Density 0.005%

    No Known Activations