© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 127676
    Prev
    Next
    INDEX
    Explanations

    occurrences of numerical values

    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
    ylko
    -0.07
     Dirt
    -0.06
    ailability
    -0.06
    ÏģÏį
    -0.06
     Washer
    -0.06
    ListOf
    -0.06
     Whilst
    -0.06
     Nero
    -0.06
    Gravity
    -0.06
    [current
    -0.06
    POSITIVE LOGITS
    kee
    0.08
    adel
    0.07
    trs
    0.07
    avs
    0.07
    ovich
    0.06
    acin
    0.06
    zs
    0.06
     cái
    0.06
    _SIGNAL
    0.06
     Orient
    0.06
    Activations Density 0.000%

    No Known Activations