© 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. 127617
    Prev
    Next
    INDEX
    Explanations

    expressions indicating personal experience or narrative

    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
    LARI
    -0.08
    aft
    -0.07
    afone
    -0.07
    atos
    -0.07
    Parcelable
    -0.07
    <quote
    -0.07
    toFloat
    -0.07
    apot
    -0.07
    apons
    -0.07
    uzzi
    -0.07
    POSITIVE LOGITS
     probably
    0.08
     tell
    0.07
     talk
    0.07
     any
    0.06
     you
    0.06
     or
    0.06
     anytime
    0.06
     told
    0.06
     themselves
    0.06
    probably
    0.06
    Activations Density 0.009%

    No Known Activations