© 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. 2971
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude

    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
    oro
    -0.07
     selber
    -0.06
     affairs
    -0.06
    yk
    -0.06
    307
    -0.06
    onth
    -0.06
    .slides
    -0.06
    inery
    -0.06
    ectors
    -0.06
    ainen
    -0.06
    POSITIVE LOGITS
     opportunity
    0.07
    assin
    0.07
    readcr
    0.07
    ipar
    0.07
    ipa
    0.06
     opportunities
    0.06
    Ability
    0.06
     ability
    0.06
    iez
    0.06
    zcze
    0.06
    Activations Density 0.006%

    No Known Activations