© 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. 70834
    Prev
    Next
    INDEX
    Explanations

    mentions of specific dates or timelines

    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
    aylight
    -0.07
     Gio
    -0.07
    arpa
    -0.07
    emailer
    -0.07
    aran
    -0.07
    ectl
    -0.07
    _PRI
    -0.07
    Gro
    -0.07
    ucken
    -0.06
    елик
    -0.06
    POSITIVE LOGITS
    份
    0.11
     Fool
    0.07
    ures
    0.07
    /A
    0.07
    наÑĤ
    0.06
    /O
    0.06
    201
    0.06
     Madness
    0.06
    åºķ
    0.06
    long
    0.06
    Activations Density 0.218%

    No Known Activations