© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 55568
    Prev
    Next
    INDEX
    Explanations

    specific numeric identifiers, particularly those related to measurements or counts

    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
    eenth
    -0.10
    ibold
    -0.07
    azen
    -0.06
    argas
    -0.06
    een
    -0.06
    uese
    -0.06
     Homes
    -0.06
    OffsetTable
    -0.06
    nds
    -0.06
    arena
    -0.06
    POSITIVE LOGITS
    orte
    0.07
    il
    0.07
    linger
    0.07
    /method
    0.06
    owell
    0.06
    inho
    0.06
    roduction
    0.06
    ãĥ³ãĥĹ
    0.06
    Äĥn
    0.06
     Canonical
    0.06
    Activations Density 0.035%

    No Known Activations