Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 29064
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "turn" and its forms

    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
    fr
    -0.06
     recon
    -0.06
     Peru
    -0.06
     NE
    -0.05
    ube
    -0.05
    (es
    -0.05
    ulpt
    -0.05
     Verde
    -0.05
     Fuk
    -0.05
     Dane
    -0.05
    POSITIVE LOGITS
    iani
    0.08
    ãĤ¤ãĤº
    0.08
    ¯ÃĤ
    0.08
    ActiveSheet
    0.07
    ÑģÑĭлки
    0.07
    akest
    0.07
    ÙĨÚ¯ÛĮ
    0.07
    alker
    0.07
    odash
    0.07
    æ¶
    0.07
    Activations Density 0.009%

    No Known Activations