© 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. 74285
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Mol" and its variations along with references to related names

    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
    elas
    -0.07
    ãĤĥ
    -0.07
    ırı
    -0.07
    rink
    -0.07
    dbuf
    -0.07
    specifier
    -0.07
    /stdc
    -0.07
    Reuse
    -0.07
    BuilderInterface
    -0.07
    ously
    -0.07
    POSITIVE LOGITS
    asses
    0.07
    ulton
    0.06
     b
    0.06
    tep
    0.06
    ster
    0.06
     ped
    0.06
     PRES
    0.06
    ly
    0.06
     fe
    0.06
    STER
    0.06
    Activations Density 0.008%

    No Known Activations