© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 28966
    Prev
    Next
    INDEX
    Explanations

    references to influential historical figures and their impact on society

    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
    folios
    -0.08
    ByVersion
    -0.08
    akah
    -0.08
    ä¸Ģç§į
    -0.07
    etwork
    -0.07
    .crm
    -0.07
    opsis
    -0.07
     Comey
    -0.07
    apur
    -0.07
    Łèĥ½
    -0.07
    POSITIVE LOGITS
     others
    0.07
     anybody
    0.07
     Robert
    0.06
     Rob
    0.06
     John
    0.06
     anyone
    0.06
     myself
    0.06
     rant
    0.06
     Tune
    0.06
     dispar
    0.06
    Activations Density 0.070%

    No Known Activations