© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 1120
    Prev
    Next
    INDEX
    Explanations

    conjunctions and names of family members

    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
    unky
    -0.07
     BUF
    -0.07
    alin
    -0.07
    leta
    -0.06
    arda
    -0.06
    lý
    -0.06
    andler
    -0.06
    ós
    -0.06
     koc
    -0.06
    pace
    -0.06
    POSITIVE LOGITS
     Cloth
    0.07
     Courtesy
    0.07
    ENSOR
    0.06
    iets
    0.06
    enda
    0.06
    @nate
    0.06
    ombo
    0.06
    onomy
    0.06
    ifax
    0.06
    ãĥ¼ãĥĭ
    0.06
    Activations Density 0.006%

    No Known Activations