© 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. 106562
    Prev
    Next
    INDEX
    Explanations

    occurrences and variations of the substring "iss" in different 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
    e
    -0.08
    ox
    -0.08
    ales
    -0.08
    ocht
    -0.08
    ores
    -0.08
    oft
    -0.08
    emi
    -0.08
    ohl
    -0.07
    eor
    -0.07
    het
    -0.07
    POSITIVE LOGITS
    linger
    0.07
    enschaft
    0.07
    ling
    0.07
    ar
    0.07
    eldorf
    0.07
    ailable
    0.06
    ed
    0.06
    ess
    0.06
    wolf
    0.06
     fur
    0.06
    Activations Density 0.022%

    No Known Activations