© 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. 40608
    Prev
    Next
    INDEX
    Explanations

    references to numerical data and values related to technical concepts

    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
    vik
    -0.08
     haline
    -0.07
    _LS
    -0.07
     sav
    -0.07
    odash
    -0.06
    -|
    -0.06
    efe
    -0.06
    ooled
    -0.06
    ogany
    -0.06
     confirm
    -0.06
    POSITIVE LOGITS
     sufficient
    0.12
     enough
    0.11
     hopefully
    0.11
     Enough
    0.10
     surely
    0.10
     Surely
    0.09
     ample
    0.09
     plenty
    0.09
     Suff
    0.08
     covers
    0.08
    Activations Density 0.040%

    No Known Activations