© 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 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. 93752
    Prev
    Next
    INDEX
    Explanations

    terms related to change and progress

    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
    nis
    -0.09
    inals
    -0.07
    itsu
    -0.07
    oice
    -0.07
    fait
    -0.07
    izia
    -0.07
    fal
    -0.07
     zby
    -0.06
    wu
    -0.06
    iets
    -0.06
    POSITIVE LOGITS
    arily
    0.10
    /dev
    0.08
    627
    0.07
    545
    0.07
    EMENT
    0.07
     into
    0.07
     Ev
    0.07
    497
    0.07
     toward
    0.07
    asser
    0.07
    Activations Density 0.014%

    No Known Activations