© 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. 28958
    Prev
    Next
    INDEX
    Explanations

    expressions of personal experiences and emotions

    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
    太éĥİ
    -0.09
    кÑĸн
    -0.08
    å¹¹
    -0.08
     поÑģÑĤоÑıнно
    -0.08
    мовÑĸÑĢ
    -0.08
    cheid
    -0.07
    ntax
    -0.07
    ียว
    -0.07
     plá
    -0.07
    enco
    -0.07
    POSITIVE LOGITS
     sometimes
    0.10
     even
    0.09
    Sometimes
    0.09
     Sometimes
    0.09
     depending
    0.08
    -times
    0.08
    even
    0.07
     occasionally
    0.07
    sometimes
    0.07
     sogar
    0.07
    Activations Density 0.027%

    No Known Activations