© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 3724
    Prev
    Next
    INDEX
    Explanations

    references to specific names or titles

    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
    usz
    -0.08
    upa
    -0.08
    roc
    -0.07
    ÙħاÙĨÛĮ
    -0.07
    TING
    -0.07
    upal
    -0.07
    umann
    -0.07
    isset
    -0.07
    ters
    -0.07
    uar
    -0.07
    POSITIVE LOGITS
    naire
    0.13
    ality
    0.12
    nement
    0.10
    nel
    0.10
    naires
    0.10
    nal
    0.10
    imbus
    0.09
    nelle
    0.09
    ni
    0.08
    neau
    0.08
    Activations Density 0.042%

    No Known Activations