© 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. 84147
    Prev
    Next
    INDEX
    Explanations

    key milestone events in a developmental or innovative context

    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
    emet
    -0.07
    овеÑĢ
    -0.07
    stry
    -0.06
    imbus
    -0.06
    .Throw
    -0.06
    ÙĤÙħ
    -0.06
    Ìĥ
    -0.06
     kut
    -0.06
     puff
    -0.06
     NotSupportedException
    -0.06
    POSITIVE LOGITS
    leitung
    0.06
    ourn
    0.06
    лÑıв
    0.06
    iday
    0.06
    ibia
    0.06
    749
    0.06
    lator
    0.06
    ÑĮ
    0.06
    Ñıк
    0.06
    peater
    0.06
    Activations Density 0.000%

    No Known Activations