© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 87209
    Prev
    Next
    INDEX
    Explanations

    phrases indicating repetition or emphasis in contexts discussing conditions or examples

    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
    Äįem
    -0.07
    _GRANTED
    -0.07
    enburg
    -0.07
    ×¢
    -0.07
     acquaint
    -0.06
    erts
    -0.06
    uesta
    -0.06
    ằng
    -0.06
    FromString
    -0.06
    /REC
    -0.06
    POSITIVE LOGITS
     situations
    0.13
     situation
    0.12
    æĥħåĨµ
    0.10
     circumstances
    0.10
     cases
    0.10
     scenario
    0.10
     Situation
    0.10
     scenarios
    0.10
     Scenario
    0.09
     casos
    0.08
    Activations Density 0.010%

    No Known Activations