© 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. 9-LLAMASCOPE-RES-131K
    11. 95734
    Prev
    Next
    INDEX
    Explanations

    terms related to infrastructure categorization and evaluation

    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
    ree
    -0.07
    ueva
    -0.06
    subclass
    -0.06
    adt
    -0.06
    iens
    -0.06
    igu
    -0.06
    sert
    -0.06
     Voltage
    -0.06
    igor
    -0.06
    ³
    -0.06
    POSITIVE LOGITS
    qli
    0.07
    ForRow
    0.07
    ingle
    0.07
    alon
    0.06
    .scalablytyped
    0.06
     ÏĩÏİ
    0.06
    phalt
    0.06
    OfDay
    0.06
    hire
    0.06
    anc
    0.06
    Activations Density 0.029%

    No Known Activations