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. 9-LLAMASCOPE-RES-131K
    6. 96275
    Prev
    Next
    INDEX
    Explanations

    references to laws and legislation

    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
    hof
    -0.07
    essen
    -0.07
    oves
    -0.07
    /back
    -0.07
    INU
    -0.07
    룬
    -0.07
    rib
    -0.07
    apolis
    -0.07
    maal
    -0.06
    ع
    -0.06
    POSITIVE LOGITS
    fully
    0.13
    /reg
    0.07
    anh
    0.07
    ombo
    0.07
    MLE
    0.07
    rf
    0.07
    fulness
    0.07
    rchive
    0.07
    iterr
    0.07
    /method
    0.07
    Activations Density 0.041%

    No Known Activations