© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 88124
    Prev
    Next
    INDEX
    Explanations

    terms related to food, specifically various "cater" forms or references to "materia" and its derivatives

    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
    sert
    -0.09
    adia
    -0.07
    abwe
    -0.07
    å®Ĺ
    -0.07
    íݸ
    -0.07
    shire
    -0.07
    elib
    -0.06
    ató
    -0.06
    ibal
    -0.06
    ORS
    -0.06
    POSITIVE LOGITS
    pillar
    0.13
    -corner
    0.08
    wheel
    0.07
    ina
    0.07
    ohana
    0.07
    pill
    0.06
    ofilm
    0.06
    andle
    0.06
    uchos
    0.06
    corner
    0.06
    Activations Density 0.008%

    No Known Activations