© 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. 81030
    Prev
    Next
    INDEX
    Explanations

    issues or complexities related to governance and measurement

    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
    alse
    -0.06
    acha
    -0.06
     Jer
    -0.06
    icast
    -0.06
    chaft
    -0.06
    actice
    -0.06
    enic
    -0.06
     finishing
    -0.05
     completion
    -0.05
    idebar
    -0.05
    POSITIVE LOGITS
     becomes
    0.16
     become
    0.14
    bec
    0.13
     Become
    0.10
     begins
    0.10
     ÑģÑĤановиÑĤÑģÑı
    0.10
     наÑĩинаеÑĤ
    0.10
     becoming
    0.10
    Become
    0.09
     Bec
    0.09
    Activations Density 0.150%

    No Known Activations