© 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. 3068
    Prev
    Next
    INDEX
    Explanations

    mentions of government departments or organizations

    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
    cess
    -0.08
    CESS
    -0.07
    RLF
    -0.07
    ozem
    -0.07
    czy
    -0.07
    emma
    -0.07
    fall
    -0.07
    ictor
    -0.07
    uther
    -0.06
    abis
    -0.06
    POSITIVE LOGITS
    alist
    0.08
    al
    0.08
     of
    0.08
    artment
    0.07
    aines
    0.07
    aux
    0.07
    ally
    0.06
     Parks
    0.06
    so
    0.06
    alm
    0.06
    Activations Density 0.014%

    No Known Activations