© 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. 83280
    Prev
    Next
    INDEX
    Explanations

    adverbs and modifiers that amplify descriptions

    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
    ries
    -0.08
    NOWLED
    -0.08
    elige
    -0.07
    bruar
    -0.07
    ritch
    -0.07
    rig
    -0.07
    ulle
    -0.07
    RIES
    -0.07
    ventus
    -0.07
    ReuseIdentifier
    -0.07
    POSITIVE LOGITS
    illo
    0.07
     minim
    0.06
     qualified
    0.06
    FTA
    0.06
    (disposing
    0.06
    æĿľ
    0.06
    _KEYS
    0.06
    æĵ¦
    0.06
     Bonds
    0.05
    اگ
    0.05
    Activations Density 0.031%

    No Known Activations