© 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. 93978
    Prev
    Next
    INDEX
    Explanations

    expressions of self-love, respect, and empowerment

    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
    ze
    -0.06
    ylon
    -0.06
    .extensions
    -0.06
     ze
    -0.06
     amateurs
    -0.06
     privileged
    -0.06
     priv
    -0.06
    onet
    -0.06
    izr
    -0.06
    versed
    -0.06
    POSITIVE LOGITS
     confidence
    0.11
     Confidence
    0.10
    confidence
    0.09
     dignity
    0.09
    -esteem
    0.09
     pride
    0.09
    Self
    0.09
     self
    0.09
     SELF
    0.08
     Self
    0.08
    Activations Density 0.038%

    No Known Activations