© 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. 15-LLAMASCOPE-RES-131K
    11. 64
    Prev
    Next
    INDEX
    Explanations

    terms related to difficulty or toughness, particularly in a contextual or descriptive manner

    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
     赤
    -0.09
    veau
    -0.08
    оÑģÑĮ
    -0.07
    akis
    -0.07
     íĴ
    -0.07
    phy
    -0.07
     SetProperty
    -0.07
    ãĥ©ãĥ³ãĥī
    -0.07
    adel
    -0.06
    ÏĢε
    -0.06
    POSITIVE LOGITS
     hard
    0.11
     Hard
    0.11
    -hard
    0.11
    Hard
    0.10
    _hard
    0.09
    hard
    0.09
     HARD
    0.08
     hardness
    0.08
     harder
    0.08
     hardest
    0.07
    Activations Density 0.041%

    No Known Activations