© 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. 118094
    Prev
    Next
    INDEX
    Explanations

    references to specific regulations and requirements in formal contexts

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

    Text describing limiting conditions, requirements, or dependencies that determine whether something is possible or impossible in a specific context.

    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
    ÑĨен
    -0.08
    ساÙĨ
    -0.07
    znám
    -0.07
    _mD
    -0.07
    èĽĽ
    -0.07
    CHEDULE
    -0.07
    _invoke
    -0.07
    ÙĬÙĥا
    -0.06
     á»ķn
    -0.06
    _mE
    -0.06
    POSITIVE LOGITS
     cannot
    0.24
    cannot
    0.19
     unable
    0.19
     Cannot
    0.19
     imposs
    0.18
    æĹłæ³ķ
    0.17
    Cannot
    0.17
     impossible
    0.16
    ä¸įèĥ½
    0.16
     inability
    0.15
    Activations Density 0.159%

    No Known Activations