© 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. 40317
    Prev
    Next
    INDEX
    Explanations

    phrases related to confidence and belief in oneself

    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
    eward
    -0.07
    amacare
    -0.07
    .qq
    -0.07
    exus
    -0.07
    uell
    -0.07
    dek
    -0.06
    opal
    -0.06
    unami
    -0.06
    elic
    -0.06
    uman
    -0.06
    POSITIVE LOGITS
     confidence
    0.23
     Confidence
    0.21
    confidence
    0.20
     confident
    0.19
    -confidence
    0.18
     confidently
    0.14
     faith
    0.13
    ä¿¡
    0.13
     ä¿¡
    0.12
    belief
    0.11
    Activations Density 0.099%

    No Known Activations