© 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. 3890
    Prev
    Next
    INDEX
    Explanations

    timestamps and date references

    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
    orta
    -0.06
    ortic
    -0.06
     зов
    -0.06
    ield
    -0.06
     Nej
    -0.06
    ãĤĩ
    -0.06
    alem
    -0.06
    kud
    -0.06
     pretext
    -0.06
    cheme
    -0.06
    POSITIVE LOGITS
    iostream
    0.06
     desper
    0.06
    ileo
    0.06
    даÑĤ
    0.06
    DTD
    0.06
    opoulos
    0.06
    iselect
    0.06
    precation
    0.06
    iar
    0.05
    .demo
    0.05
    Activations Density 0.004%

    No Known Activations