© 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. 15-LLAMASCOPE-RES-131K
    11. 104073
    Prev
    Next
    INDEX
    Explanations

    expressions relating to experiences of starting anew or relocation

    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
    ãĥ¼ãĥ
    -0.07
     ÃĩaÄŁ
    -0.07
    OUNCE
    -0.07
    ustil
    -0.07
    iscard
    -0.07
    ủng
    -0.07
    onical
    -0.07
    ugins
    -0.07
    ihat
    -0.07
    inston
    -0.07
    POSITIVE LOGITS
    antan
    0.07
     Shay
    0.06
    elt
    0.06
    359
    0.06
     somebody
    0.06
     cheat
    0.06
    heet
    0.06
    ityEngine
    0.06
     oneself
    0.06
     Benn
    0.06
    Activations Density 0.014%

    No Known Activations