© 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. 83426
    Prev
    Next
    INDEX
    Explanations

    instances of the word "here" indicating a focus on location or context within the text

    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
    ses
    -0.06
     partial
    -0.06
    portion
    -0.05
    uluk
    -0.05
     ready
    -0.05
     tend
    -0.05
     area
    -0.05
    chin
    -0.05
     multiplier
    -0.05
    Ïħ
    -0.05
    POSITIVE LOGITS
     заÑģÑĤ
    0.08
    'gc
    0.07
    ina
    0.07
    onas
    0.07
    jÅ¡ÃŃ
    0.07
    baÅŁ
    0.07
    unto
    0.07
    after
    0.07
    bens
    0.07
    assic
    0.07
    Activations Density 0.018%

    No Known Activations