© 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. 60802
    Prev
    Next
    INDEX
    Explanations

    end punctuation marks

    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
    ypy
    -0.08
    ahi
    -0.07
    ungs
    -0.07
    cript
    -0.06
    ahat
    -0.06
    ãĥ§
    -0.06
    amina
    -0.06
    ÑĪка
    -0.06
    iculos
    -0.06
    ãĥ¼ãĥĹ
    -0.06
    POSITIVE LOGITS
    annels
    0.07
    CESS
    0.07
    è¢
    0.06
     gar
    0.06
    spin
    0.06
     moreover
    0.06
    æ©
    0.06
     Wik
    0.06
     gint
    0.06
    otec
    0.06
    Activations Density 0.000%

    No Known Activations