© 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. 9-LLAMASCOPE-RES-131K
    6. 96466
    Prev
    Next
    INDEX
    Explanations

    terms related to software features and functions

    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
    uzu
    -0.08
    vÃŃ
    -0.07
    /lg
    -0.07
    isin
    -0.07
     kolo
    -0.07
    orch
    -0.07
     Hlav
    -0.06
    .easing
    -0.06
    uder
    -0.06
     huy
    -0.06
    POSITIVE LOGITS
    ves
    0.06
    olec
    0.06
    aghan
    0.06
    iana
    0.06
    dale
    0.06
     Bra
    0.06
    ryn
    0.06
    arel
    0.06
    ador
    0.05
     Epic
    0.05
    Activations Density 0.022%

    No Known Activations