© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 84880
    Prev
    Next
    INDEX
    Explanations

    terms related to elevated living spaces or 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
    er
    -0.09
    eru
    -0.09
    ãģĦãĤĭ
    -0.08
    has
    -0.07
    erca
    -0.07
    erer
    -0.07
    antz
    -0.07
    rnd
    -0.07
    hit
    -0.07
    raph
    -0.07
    POSITIVE LOGITS
    entimes
    0.16
    ers
    0.10
    sch
    0.09
    shire
    0.08
    sy
    0.08
    iness
    0.08
    eners
    0.08
    ests
    0.07
    ersh
    0.07
    acular
    0.07
    Activations Density 0.021%

    No Known Activations