© 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. 5-LLAMASCOPE-RES-131K
    11. 126897
    Prev
    Next
    INDEX
    Explanations

    instances of the word "cross" and its variations, indicating themes of transitions or obstacles

    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
    uitka
    -0.07
    omite
    -0.07
    upo
    -0.07
    semb
    -0.06
    ski
    -0.06
    nor
    -0.06
    ordova
    -0.06
    iferay
    -0.06
    LEC
    -0.06
    iona
    -0.06
    POSITIVE LOGITS
    aber
    0.08
    arin
    0.08
    _Reference
    0.07
    è¯ī
    0.07
    illin
    0.07
    appropri
    0.07
     Winston
    0.06
    opus
    0.06
    ÅĤÄħ
    0.06
    881
    0.06
    Activations Density 0.008%

    No Known Activations