© 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. 15-LLAMASCOPE-RES-131K
    6. 601
    Prev
    Next
    INDEX
    Explanations

    occurrences of conjunctions and phrases that suggest relationships or connections

    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
    ocu
    -0.07
    .pb
    -0.07
    onet
    -0.07
    oulos
    -0.06
    _pb
    -0.06
     Kush
    -0.06
    TL
    -0.06
     Panther
    -0.06
    isque
    -0.06
    quisites
    -0.06
    POSITIVE LOGITS
    .fig
    0.07
    tember
    0.07
    oney
    0.06
    avad
    0.06
    402
    0.06
    izo
    0.06
    794
    0.06
    omes
    0.06
    611
    0.06
    inea
    0.06
    Activations Density 0.022%

    No Known Activations