© 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. 40196
    Prev
    Next
    INDEX
    Explanations

    expressions of hope or belief regarding improvement or relief from suffering

    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
    866
    -0.08
    ruh
    -0.08
    ãĤ¤ãĥī
    -0.08
    iid
    -0.07
    vider
    -0.07
    amel
    -0.07
    quoise
    -0.07
    emmel
    -0.07
    azor
    -0.07
    emm
    -0.07
    POSITIVE LOGITS
     somehow
    0.12
     thereby
    0.12
     might
    0.07
     Surely
    0.07
    might
    0.07
     will
    0.07
    will
    0.07
    è¿Ļæł·
    0.06
     surely
    0.06
     better
    0.06
    Activations Density 0.030%

    No Known Activations