© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 88002
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "on" in various contexts

    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
    oler
    -0.07
     åĮ
    -0.06
     pleas
    -0.06
    eview
    -0.06
    ideshow
    -0.06
    .IsAny
    -0.06
    SPATH
    -0.06
    BOOLE
    -0.06
    BOVE
    -0.06
    orsch
    -0.06
    POSITIVE LOGITS
    yre
    0.07
    Medium
    0.07
    Instagram
    0.07
     Instagram
    0.07
    ruž
    0.07
    yk
    0.06
    пÑĢиклад
    0.06
     Medium
    0.06
    ĤŃ
    0.06
     his
    0.06
    Activations Density 0.007%

    No Known Activations