© 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. 3854
    Prev
    Next
    INDEX
    Explanations

    references to art, community events, and projects that promote inclusivity and support

    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
    éĻ¢
    -0.07
    ,[],
    -0.06
     ones
    -0.06
     background
    -0.06
    592
    -0.06
    Degree
    -0.06
     Tob
    -0.05
     minute
    -0.05
     TEX
    -0.05
     Jako
    -0.05
    POSITIVE LOGITS
     initiative
    0.07
    isode
    0.07
     platform
    0.07
    acyj
    0.07
    oproject
    0.07
     project
    0.07
    µľ
    0.07
     series
    0.07
     program
    0.07
     experiment
    0.07
    Activations Density 0.037%

    No Known Activations