Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5272
    Prev
    Next
    INDEX
    Explanations

    words related to "convergence" and its variations

    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
    arl
    -0.08
    ×ķ
    -0.06
    dependence
    -0.06
    ÙĥÙĪÙĨ
    -0.06
    asl
    -0.06
    autop
    -0.06
    ĺIJ
    -0.06
    CREMENT
    -0.06
    θη
    -0.06
    pawn
    -0.06
    POSITIVE LOGITS
    igli
    0.07
    ä¹Ī
    0.07
    rovers
    0.07
    anten
    0.07
    âĸ²
    0.07
    createCommand
    0.07
    jug
    0.07
    roe
    0.07
    تر
    0.07
    adian
    0.06
    Activations Density 0.030%

    No Known Activations