© 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. 30270
    Prev
    Next
    INDEX
    Explanations

    phrases indicating positive recommendations or options

    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
    mts
    -0.07
    phis
    -0.06
    idian
    -0.06
     Horton
    -0.06
    ä»ĺãģij
    -0.06
    lsi
    -0.06
    filer
    -0.06
     coun
    -0.06
    .locals
    -0.06
    541
    -0.06
    POSITIVE LOGITS
    ropa
    0.07
    299
    0.07
    agal
    0.06
     ello
    0.06
    RESS
    0.06
    lo
    0.06
    æ²Ļ
    0.06
     Sever
    0.06
    SFML
    0.06
    zyst
    0.06
    Activations Density 0.036%

    No Known Activations