© 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. 125083
    Prev
    Next
    INDEX
    Explanations

    indicators of navigation or sequential content within articles

    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
    ancellable
    -0.07
    ÙģاÙĤ
    -0.07
    kit
    -0.07
    .onView
    -0.07
    egas
    -0.07
    åĿĤ
    -0.07
    ijľ
    -0.07
    ÑĥÑĢÑģ
    -0.07
    anos
    -0.07
    lient
    -0.07
    POSITIVE LOGITS
    egend
    0.06
     ting
    0.06
     Charg
    0.06
    adius
    0.06
    luž
    0.06
    akis
    0.05
     wel
    0.05
    atre
    0.05
    BI
    0.05
    weis
    0.05
    Activations Density 0.003%

    No Known Activations