© 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. 106907
    Prev
    Next
    INDEX
    Explanations

    expressions related to personal experiences and metaphors

    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
    jis
    -0.07
    [js
    -0.07
     consts
    -0.07
    å®
    -0.07
     <<-
    -0.07
     Gay
    -0.07
    лав
    -0.06
    istrovstvÃŃ
    -0.06
    åħ±åIJĮ
    -0.06
    á»ķ
    -0.06
    POSITIVE LOGITS
     clap
    0.08
     STD
    0.08
     partners
    0.07
     partnered
    0.07
     partner
    0.07
    idal
    0.06
     anatom
    0.06
    mue
    0.06
    partner
    0.06
     ST
    0.06
    Activations Density 0.089%

    No Known Activations