© 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. 83053
    Prev
    Next
    INDEX
    Explanations

    concepts related to philosophical inquiries and existential questions

    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
    zek
    -0.07
    abel
    -0.07
    à¹Ģà¸ļ
    -0.07
    phinx
    -0.06
    _ARB
    -0.06
    obil
    -0.06
    ABEL
    -0.06
     ben
    -0.06
    ³
    -0.06
    elu
    -0.06
    POSITIVE LOGITS
     mover
    0.06
    MenuBar
    0.06
    uki
    0.06
     buck
    0.06
     tracing
    0.06
    /start
    0.06
     chain
    0.06
     gravid
    0.06
     claim
    0.06
    ichert
    0.06
    Activations Density 0.005%

    No Known Activations