© 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. 60177
    Prev
    Next
    INDEX
    Explanations

    references to distinct historical periods or "eras."

    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
    ryo
    -0.08
    agers
    -0.07
    rawn
    -0.07
    erman
    -0.07
    ammer
    -0.07
    weed
    -0.07
    cri
    -0.07
    ers
    -0.07
    arrants
    -0.07
    yan
    -0.07
    POSITIVE LOGITS
    -long
    0.11
    odelist
    0.09
    -old
    0.09
    icals
    0.08
    ichel
    0.08
    ë³Ħ
    0.07
    imitive
    0.07
    æľ«
    0.07
    åĪ¥
    0.07
    imli
    0.07
    Activations Density 0.008%

    No Known Activations