© 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. 93680
    Prev
    Next
    INDEX
    Explanations

    variations of the word "hold" in different contexts

    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
     Mellon
    -0.07
    esis
    -0.07
    kol
    -0.07
    ially
    -0.07
    leme
    -0.07
     hypothetical
    -0.07
     holistic
    -0.07
    bero
    -0.07
    etti
    -0.07
    ordin
    -0.07
    POSITIVE LOGITS
     sway
    0.11
    iday
    0.11
    reds
    0.09
    fast
    0.08
    çºĮ
    0.08
    ä½ı
    0.08
     accountable
    0.08
    erness
    0.08
    ings
    0.08
     onto
    0.08
    Activations Density 0.032%

    No Known Activations