© 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. 15-LLAMASCOPE-RES-131K
    11. 103579
    Prev
    Next
    INDEX
    Explanations

    references to specific places and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Feature descriptions and key selling points in product/service listings, typically appearing as concise statements at the end of descriptions.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    aug
    -0.06
    or
    -0.06
    lust
    -0.06
     latter
    -0.06
     this
    -0.05
    agan
    -0.05
    718
    -0.05
     _
    -0.05
     ex
    -0.05
     these
    -0.05
    POSITIVE LOGITS
    ãģªãĤĭ
    0.08
    _constants
    0.07
    âĢĮسÛĮ
    0.07
     GenerationType
    0.07
    .EN
    0.07
    autiful
    0.07
    ición
    0.07
    esel
    0.07
    ureau
    0.07
    ceptar
    0.07
    Activations Density 0.015%

    No Known Activations