© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 60794
    Prev
    Next
    INDEX
    Explanations

    elements related to daily routines and personal reflections

    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
     will
    -0.09
     should
    -0.07
    'll
    -0.07
    ould
    -0.07
    onna
    -0.06
     potentially
    -0.06
     may
    -0.06
    ngth
    -0.06
    769
    -0.06
    should
    -0.06
    POSITIVE LOGITS
    æĪijçļĦ
    0.08
    æĺ¯æĪij
    0.07
     sometimes
    0.07
     моÑĹ
    0.07
     иногда
    0.07
     помогаеÑĤ
    0.07
     my
    0.07
    ometimes
    0.07
    sometimes
    0.07
    LEM
    0.07
    Activations Density 0.048%

    No Known Activations