© 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. 15-LLAMASCOPE-RES-131K
    6. 103616
    Prev
    Next
    INDEX
    Explanations

    aspects related to character development and depth in storytelling

    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
    anela
    -0.08
    lacak
    -0.08
    ãĥ¼ãĥIJ
    -0.07
    ospace
    -0.07
    rement
    -0.07
    rava
    -0.07
    iya
    -0.07
    punkt
    -0.07
    anz
    -0.07
    weets
    -0.07
    POSITIVE LOGITS
     character
    0.09
     Character
    0.08
     characters
    0.08
    -char
    0.07
     characterization
    0.07
     Characters
    0.07
     olduk
    0.07
     profiles
    0.07
     flesh
    0.07
     CHARACTER
    0.07
    Activations Density 0.032%

    No Known Activations