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

    Neuronpedia

    Jacobian LensNEW
    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. 93848
    Prev
    Next
    INDEX
    Explanations

    terms associated with difficulty or intensity in various contexts

    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
    pek
    -0.08
    jal
    -0.07
    èĥŀ
    -0.07
    .dsl
    -0.06
    adden
    -0.06
    пеÑĩ
    -0.06
    ése
    -0.06
    isse
    -0.06
     íĴ
    -0.06
    Jur
    -0.06
    POSITIVE LOGITS
     hard
    0.14
     Hard
    0.14
    -hard
    0.13
    Hard
    0.13
    hard
    0.12
     HARD
    0.11
     harder
    0.10
    _hard
    0.10
    硬
    0.08
     hardest
    0.08
    Activations Density 0.022%

    No Known Activations