© 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. 86222
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to trust and belief in others

    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
    uzu
    -0.08
    assed
    -0.07
    ifr
    -0.07
    ãİ¡
    -0.07
    quat
    -0.07
    cec
    -0.07
    quel
    -0.07
    bens
    -0.07
    ivan
    -0.07
    ugu
    -0.07
    POSITIVE LOGITS
    ingly
    0.08
    worth
    0.08
    worthy
    0.08
    ably
    0.08
     trust
    0.08
     trusting
    0.07
    trust
    0.07
     enough
    0.06
     implicitly
    0.06
    fully
    0.06
    Activations Density 0.006%

    No Known Activations