© 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. 106760
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and specific formatting symbols

    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
    PURE
    -0.07
    asz
    -0.07
    iên
    -0.07
    arte
    -0.07
    eldom
    -0.07
    MOTE
    -0.06
    witter
    -0.06
     HDC
    -0.06
    ê´ij
    -0.06
    گار
    -0.06
    POSITIVE LOGITS
    oose
    0.07
    Ñģлед
    0.06
    gether
    0.06
    ана
    0.06
    agara
    0.06
    apolis
    0.06
    uers
    0.06
    odore
    0.06
     Moody
    0.05
    umbnails
    0.05
    Activations Density 0.005%

    No Known Activations