© 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. 16602
    Prev
    Next
    INDEX
    Explanations

    references to guidance or recommendations

    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
    jist
    -0.08
     konkrét
    -0.07
    éŃĤ
    -0.06
    AMESPACE
    -0.06
    607
    -0.06
    ousel
    -0.06
    isateur
    -0.06
    534
    -0.06
     ведÑĮ
    -0.06
    protobuf
    -0.06
    POSITIVE LOGITS
    etrain
    0.07
    ange
    0.06
    oot
    0.06
    alg
    0.06
    xn
    0.06
    obot
    0.06
    odef
    0.06
    سÙĦ
    0.06
    /renderer
    0.06
    antry
    0.06
    Activations Density 0.000%

    No Known Activations