© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 58803
    Prev
    Next
    INDEX
    Explanations

    mentions of individual characters or people, particularly focusing on their actions and traits

    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
     fool
    -0.06
     fon
    -0.06
     increasingly
    -0.06
     thereby
    -0.06
     rst
    -0.05
    orage
    -0.05
    ://
    -0.05
    oub
    -0.05
    jist
    -0.05
    uzzi
    -0.05
    POSITIVE LOGITS
    aler
    0.07
    âĢ¦âĢ¦ãĢĤ
    0.07
    imi
    0.07
    raft
    0.07
    mia
    0.07
    "is
    0.07
    ABCDEFGHI
    0.07
    Fit
    0.07
    843
    0.07
    _tokenize
    0.07
    Activations Density 0.045%

    No Known Activations