© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 40297
    Prev
    Next
    INDEX
    Explanations

    citations and publication information in academic writing

    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
    blr
    -0.07
    esson
    -0.07
    -ÑĤо
    -0.07
     McDon
    -0.07
    anim
    -0.07
    à¸ģร
    -0.07
    uren
    -0.06
    OUCH
    -0.06
    izen
    -0.06
    viz
    -0.06
    POSITIVE LOGITS
     bulk
    0.06
    obo
    0.06
    shan
    0.06
    bulk
    0.05
     --
    0.05
     mastur
    0.05
     Ferd
    0.05
    ÙĥاÙĨ
    0.05
    geois
    0.05
     massage
    0.05
    Activations Density 0.004%

    No Known Activations