Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43776
    Prev
    Next
    INDEX
    Explanations

    references to educational institutions and their historical context

    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
     whose
    -0.08
     Erotik
    -0.06
    whose
    -0.06
    tvrt
    -0.06
     unless
    -0.05
     Woche
    -0.05
     Auswahl
    -0.05
     which
    -0.05
     Antworten
    -0.05
    vertime
    -0.05
    POSITIVE LOGITS
     estava
    0.12
     fue
    0.11
     estaba
    0.11
     recebe
    0.10
     era
    0.10
     était
    0.10
     foi
    0.10
     possui
    0.10
     começ
    0.10
     se
    0.10
    Activations Density 0.120%

    No Known Activations