© 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. 5-LLAMASCOPE-RES-131K
    11. 126920
    Prev
    Next
    INDEX
    Explanations

    verbs that indicate physical force or movement

    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
    specifier
    -0.08
    _stdio
    -0.08
    veau
    -0.08
    icus
    -0.07
    uron
    -0.07
    isdiction
    -0.07
    æķ·
    -0.07
    aits
    -0.07
    isman
    -0.07
    º¼
    -0.07
    POSITIVE LOGITS
    æ¶
    0.06
    sten
    0.06
    anka
    0.06
     or
    0.06
    129
    0.06
    ãĥ³ãĥĩ
    0.06
    137
    0.06
    back
    0.06
     congr
    0.05
     suitable
    0.05
    Activations Density 0.015%

    No Known Activations