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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 128909
    Prev
    Next
    INDEX
    Explanations

    terms related to concessions and conjugation

    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
     вк
    -0.07
    ãģĦãĤĭ
    -0.07
     latter
    -0.07
    OrDefault
    -0.07
    istry
    -0.07
    lier
    -0.06
    scribe
    -0.06
    anou
    -0.06
     Excell
    -0.06
    icity
    -0.06
    POSITIVE LOGITS
    aire
    0.09
    ional
    0.08
    istent
    0.07
    itis
    0.07
    ible
    0.07
    ÑģÑı
    0.07
    ette
    0.07
    738
    0.07
    ively
    0.07
    ãĥ«ãĥī
    0.06
    Activations Density 0.030%

    No Known Activations