© 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. 15-LLAMASCOPE-RES-131K
    11. 90600
    Prev
    Next
    INDEX
    Explanations

    phrases that express a minimum standard or requirement

    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
    ozilla
    -0.07
    .au
    -0.07
    aeper
    -0.07
    ntag
    -0.07
    /from
    -0.07
    aisy
    -0.07
    "crypto
    -0.06
    пон
    -0.06
    chts
    -0.06
    _closure
    -0.06
    POSITIVE LOGITS
    poÄįet
    0.06
    ullen
    0.06
    utor
    0.06
    tras
    0.06
     now
    0.06
    andi
    0.06
    visibility
    0.06
     Consolid
    0.06
     finally
    0.06
     Useful
    0.05
    Activations Density 0.004%

    No Known Activations