© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 118842
    Prev
    Next
    INDEX
    Explanations

    concepts and expressions related to acceptance and self-acceptance

    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
    boss
    -0.07
    flix
    -0.07
    ve
    -0.07
    oron
    -0.06
    escape
    -0.06
    escaping
    -0.06
    ÑĶ
    -0.06
    ef
    -0.06
    etwork
    -0.06
     uplat
    -0.06
    POSITIVE LOGITS
     reality
    0.09
     fact
    0.08
     Reality
    0.08
     realities
    0.08
     rằng
    0.07
    _fact
    0.07
     inevitable
    0.07
     facts
    0.07
    Fact
    0.07
     Fact
    0.07
    Activations Density 0.010%

    No Known Activations