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

    Neuronpedia

    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. 22-LLAMASCOPE-RES-131K
    11. 3661
    Prev
    Next
    INDEX
    Explanations

    phrases indicating examples or specific instances

    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
    太éĥİ
    -0.08
     thing
    -0.08
    ama
    -0.07
     odv
    -0.07
    ÑĩÑĥк
    -0.07
    restriction
    -0.07
    SCII
    -0.07
    ame
    -0.07
    exo
    -0.06
    ãģ¨ãģĵãĤį
    -0.06
    POSITIVE LOGITS
     cases
    0.20
    cases
    0.16
     case
    0.15
     Cases
    0.15
     instances
    0.14
     casos
    0.13
     situations
    0.13
    case
    0.12
     circumstances
    0.12
     scenarios
    0.12
    Activations Density 0.023%

    No Known Activations