© 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. 2653
    Prev
    Next
    INDEX
    Explanations

    offers and mentions of complimentary or free services

    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
    chez
    -0.06
    _TAC
    -0.06
    оÑĢÑĥж
    -0.06
    符
    -0.06
    DOI
    -0.06
    356
    -0.06
    å¼±
    -0.06
    ahun
    -0.05
    yah
    -0.05
     ofType
    -0.05
    POSITIVE LOGITS
     pragma
    0.07
    upro
    0.07
    íݸ
    0.06
    xA
    0.06
    cip
    0.06
    celed
    0.06
    iron
    0.06
    ÅŁ
    0.06
    icrobial
    0.06
    hower
    0.06
    Activations Density 0.000%

    No Known Activations