© 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. 40680
    Prev
    Next
    INDEX
    Explanations

    expressions of enjoyment and positive experiences

    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
    ekler
    -0.09
    lesc
    -0.08
    adh
    -0.08
    cura
    -0.07
    ihn
    -0.07
    endent
    -0.07
    gnore
    -0.07
    ipop
    -0.07
    jours
    -0.07
    /lic
    -0.07
    POSITIVE LOGITS
     module
    0.07
     group
    0.07
    group
    0.07
    -module
    0.06
     activities
    0.06
    odule
    0.06
    module
    0.06
    -group
    0.06
    _module
    0.06
    cesso
    0.06
    Activations Density 0.029%

    No Known Activations