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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 106162
    Prev
    Next
    INDEX
    Explanations

    repeated references to brands, products, and specifications

    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
    avaÅŁ
    -0.07
     Mellon
    -0.07
    ìĨ
    -0.06
    é»ĺ
    -0.06
    รส
    -0.06
    surname
    -0.06
    owan
    -0.06
    pedia
    -0.06
    gger
    -0.06
    аÑĢам
    -0.06
    POSITIVE LOGITS
    ropolitan
    0.07
    ãĥ³ãĥ
    0.06
     complement
    0.06
    inel
    0.06
    736
    0.06
    UTE
    0.06
     Stad
    0.06
    mouseup
    0.06
    jar
    0.06
     IReadOnly
    0.06
    Activations Density 0.015%

    No Known Activations