© 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. 70946
    Prev
    Next
    INDEX
    Explanations

    concepts related to possession and ownership

    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
    urum
    -0.07
    ãĥĢãĤ¤
    -0.07
    ìŀ¥ìĿ´
    -0.07
    ìŀ¥
    -0.07
    renc
    -0.07
    æķ·
    -0.07
     Müz
    -0.06
     Newsp
    -0.06
    뮤
    -0.06
    $MESS
    -0.06
    POSITIVE LOGITS
    ï¼īãģ¯
    0.07
    275
    0.06
    LEE
    0.06
     fest
    0.06
     decks
    0.06
    uche
    0.06
    142
    0.06
     ê²½ìļ°
    0.06
    lew
    0.06
     will
    0.05
    Activations Density 0.055%

    No Known Activations