© 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. 15-LLAMASCOPE-RES-131K
    6. 206
    Prev
    Next
    INDEX
    Explanations

    references to software and its associated conditions or disclaimers

    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
    ema
    -0.07
    дап
    -0.07
    olla
    -0.07
    asz
    -0.07
    eldorf
    -0.07
    aphore
    -0.06
    apia
    -0.06
    wand
    -0.06
    vetica
    -0.06
    crets
    -0.06
    POSITIVE LOGITS
    .splitext
    0.06
    inea
    0.06
    PEC
    0.06
    ansson
    0.06
    arkin
    0.06
    ÃŁen
    0.06
     Soldier
    0.06
    ULONG
    0.06
     resident
    0.06
    LEC
    0.06
    Activations Density 0.000%

    No Known Activations