© 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 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. 88724
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "In" and its variations

    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
    iam
    -0.06
    ect
    -0.06
    dorf
    -0.06
     __
    -0.06
    aws
    -0.05
     resident
    -0.05
    oma
    -0.05
    chest
    -0.05
     F
    -0.05
     int
    -0.05
    POSITIVE LOGITS
    ìłĿ
    0.07
    SharedPointer
    0.07
     liners
    0.07
    psilon
    0.07
    utral
    0.07
    aniu
    0.07
    itized
    0.07
     Stateless
    0.07
     Giovanni
    0.07
    _journal
    0.06
    Activations Density 0.000%

    No Known Activations