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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 84040
    Prev
    Next
    INDEX
    Explanations

    references to frequency and quantity

    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
     Suche
    -0.07
    erli
    -0.07
    oppel
    -0.07
    ác
    -0.07
    mmc
    -0.07
    ÑĥлÑİ
    -0.07
    abase
    -0.07
    unar
    -0.06
    erb
    -0.06
    .gnu
    -0.06
    POSITIVE LOGITS
     twice
    0.12
     times
    0.11
     Twice
    0.10
    times
    0.08
     TIMES
    0.08
    次æķ°
    0.08
     ÑĢаза
    0.08
     vezes
    0.07
     Times
    0.07
    tw
    0.07
    Activations Density 0.015%

    No Known Activations