© 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. 17-LLAMASCOPE-RES-131K
    11. 16126
    Prev
    Next
    INDEX
    Explanations

    terms related to community resources, support systems, and collaborative efforts

    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
     Slater
    -0.06
    rix
    -0.06
    licted
    -0.06
    vor
    -0.06
    ether
    -0.06
    loy
    -0.06
    lys
    -0.06
    ylie
    -0.06
    ASI
    -0.06
    leaflet
    -0.06
    POSITIVE LOGITS
     called
    0.09
    åı«
    0.08
    called
    0.08
    appa
    0.07
     Called
    0.07
    ırak
    0.07
    cus
    0.07
    /wiki
    0.07
    ForResource
    0.07
    uls
    0.06
    Activations Density 0.029%

    No Known Activations