© 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. 84129
    Prev
    Next
    INDEX
    Explanations

    terms related to geometric concepts and structures

    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
    ue
    -0.08
    au
    -0.07
    udd
    -0.07
    age
    -0.07
    anto
    -0.07
    ãģĦãģ¦
    -0.06
    gle
    -0.06
     деле
    -0.06
    band
    -0.06
    rooms
    -0.06
    POSITIVE LOGITS
    rical
    0.09
    ally
    0.09
    ffen
    0.09
    ALLY
    0.08
    /ge
    0.08
    /engine
    0.07
    ebra
    0.07
    /top
    0.07
    _msgs
    0.07
    balls
    0.07
    Activations Density 0.009%

    No Known Activations