© 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. 81789
    Prev
    Next
    INDEX
    Explanations

    quantitative comparisons regarding amounts or levels

    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
    PARATOR
    -0.07
    ongs
    -0.07
    Ø©
    -0.07
    eyi
    -0.07
     or
    -0.07
    ãĤ¯ãĥĪ
    -0.06
    je
    -0.06
    523
    -0.06
    inh
    -0.06
    and
    -0.06
    POSITIVE LOGITS
    halb
    0.08
    auled
    0.08
     alike
    0.07
    /misc
    0.07
    RowAt
    0.07
    /close
    0.07
    OwnProperty
    0.07
    erde
    0.06
    irk
    0.06
    eworld
    0.06
    Activations Density 0.009%

    No Known Activations