© 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. 17-LLAMASCOPE-RES-131K
    11. 70832
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships or connections

    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
    icos
    -0.08
    ilos
    -0.07
    umatic
    -0.06
    оÑģлав
    -0.06
    keley
    -0.06
    ahas
    -0.06
    andelier
    -0.06
    uisse
    -0.06
    ÃŃg
    -0.06
    é³´
    -0.06
    POSITIVE LOGITS
    HORT
    0.06
    ampp
    0.06
    Utf
    0.06
    éijij
    0.06
    upo
    0.06
     DSM
    0.06
     ethn
    0.06
    رت
    0.06
     ADM
    0.06
    olle
    0.06
    Activations Density 0.005%

    No Known Activations