© 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. 57196
    Prev
    Next
    INDEX
    Explanations

    the word "as" indicating comparisons or equivalences

    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
    çIJ³
    -0.07
    á»ĵi
    -0.06
    iente
    -0.06
     è°
    -0.06
     خارجÙĬØ©
    -0.06
     scr
    -0.06
    urm
    -0.06
     @[
    -0.06
     consum
    -0.06
    phan
    -0.06
    POSITIVE LOGITS
    speed
    0.09
     speeds
    0.08
    éĢŁåº¦
    0.08
    Speed
    0.08
     Speed
    0.08
    .Speed
    0.08
    .speed
    0.08
    -speed
    0.07
    peed
    0.07
     speed
    0.07
    Activations Density 0.000%

    No Known Activations