© 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. 5-LLAMASCOPE-RES-131K
    11. 126043
    Prev
    Next
    INDEX
    Explanations

    terms related to living organisms or specimens

    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
    so
    -0.06
    ieder
    -0.06
    ster
    -0.06
    &S
    -0.06
    undle
    -0.06
    º
    -0.06
    ang
    -0.06
    ette
    -0.06
    InstanceOf
    -0.06
    141
    -0.06
    POSITIVE LOGITS
    ENCHMARK
    0.08
    rink
    0.07
    erta
    0.07
    .BLL
    0.07
    .DAL
    0.07
    longleftrightarrow
    0.06
    .opensource
    0.06
    ipt
    0.06
    Aware
    0.06
    æīĺ
    0.06
    Activations Density 0.007%

    No Known Activations