© 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. 120020
    Prev
    Next
    INDEX
    Explanations

    dates, particularly those related to significant events or postings

    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
    egl
    -0.08
    eres
    -0.06
    agen
    -0.06
    pes
    -0.06
    aler
    -0.06
    entin
    -0.06
    ****************************************************************************
    -0.06
    mk
    -0.06
    aches
    -0.06
     Hubb
    -0.06
    POSITIVE LOGITS
    éĥİ
    0.07
     later
    0.07
    ToFit
    0.07
    ">//
    0.07
     Later
    0.06
     permanently
    0.06
    Later
    0.06
    uisse
    0.06
    GetComponent
    0.06
    ughs
    0.06
    Activations Density 0.008%

    No Known Activations