© 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. 17-LLAMASCOPE-RES-131K
    11. 70553
    Prev
    Next
    INDEX
    Explanations

    instances of a specific repeated phrase or term

    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
    coles
    -0.07
    711
    -0.07
    cot
    -0.06
    654
    -0.06
    egt
    -0.06
    hower
    -0.06
    297
    -0.06
    /foo
    -0.06
    igest
    -0.06
    cott
    -0.06
    POSITIVE LOGITS
     Jaune
    0.07
    quer
    0.07
    disc
    0.07
     uz
    0.07
    lement
    0.06
    ground
    0.06
    nung
    0.06
    gel
    0.06
    /AP
    0.06
     Uz
    0.06
    Activations Density 0.003%

    No Known Activations