© 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. 75668
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions or intentions that involve direction or movement

    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
    istrovstvÃŃ
    -0.08
    using
    -0.07
     aba
    -0.07
    |{↵
    -0.07
    æ¡ĥ
    -0.07
    менÑĪ
    -0.07
    nock
    -0.07
    å·±
    -0.07
    _QMARK
    -0.07
    erville
    -0.07
    POSITIVE LOGITS
    for
    0.07
     for
    0.07
    ula
    0.07
     accompany
    0.07
    which
    0.07
     accompanies
    0.06
     which
    0.06
    ent
    0.06
    301
    0.06
     Nass
    0.06
    Activations Density 0.034%

    No Known Activations