© 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. 16291
    Prev
    Next
    INDEX
    Explanations

    elements related to academic work and research proposals

    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
    vla
    -0.07
    å¹ķ
    -0.07
    orthand
    -0.07
    HQ
    -0.07
    ãĥ³ãĤ¿
    -0.06
    sla
    -0.06
    åħµ
    -0.06
    ãĥ©ãĤ¤ãĥ³
    -0.06
    ocab
    -0.06
    taÅŁ
    -0.06
    POSITIVE LOGITS
     research
    0.12
     Research
    0.10
    research
    0.09
     researcher
    0.08
     project
    0.08
     researchers
    0.07
    Research
    0.07
     study
    0.07
     proposed
    0.06
     proposal
    0.06
    Activations Density 0.006%

    No Known Activations