© 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. 40814
    Prev
    Next
    INDEX
    Explanations

    descriptions of enjoyable or favorable 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
    ãģĦãĤĭ
    -0.08
    zilla
    -0.08
    .au
    -0.06
    atik
    -0.06
    _DIRS
    -0.06
    sus
    -0.06
    obao
    -0.06
    ocache
    -0.06
     mentality
    -0.06
    otate
    -0.06
    POSITIVE LOGITS
    ly
    0.11
    emente
    0.09
    -looking
    0.09
    ness
    0.09
     surprise
    0.09
     surprises
    0.09
    mente
    0.09
    LY
    0.09
     Surprise
    0.08
    ment
    0.08
    Activations Density 0.005%

    No Known Activations