© 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. 126005
    Prev
    Next
    INDEX
    Explanations

    key phrases related to foundational concepts in projects or arguments

    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
    aille
    -0.08
     fact
    -0.07
    uler
    -0.07
    ÅĻÃŃž
    -0.07
    reason
    -0.06
    -preview
    -0.06
    /npm
    -0.06
    erli
    -0.06
    érica
    -0.06
     Kel
    -0.06
    POSITIVE LOGITS
     necessary
    0.12
     needed
    0.09
     required
    0.09
    necessary
    0.09
    orex
    0.08
     desired
    0.08
    needed
    0.07
    -needed
    0.07
     Necessary
    0.07
     необÑħодим
    0.07
    Activations Density 0.032%

    No Known Activations