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. 96233
    Prev
    Next
    INDEX
    Explanations

    mentions of the brand "Mercedes-Benz"

    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
    nul
    -0.07
    LayoutManager
    -0.07
    annis
    -0.06
    iro
    -0.06
    ForMember
    -0.06
    vette
    -0.06
     pob
    -0.06
    imonials
    -0.06
    atik
    -0.06
    ucer
    -0.06
    POSITIVE LOGITS
    arget
    0.06
    лоп
    0.06
    RIORITY
    0.06
    ycz
    0.06
    ese
    0.06
     Hunts
    0.06
    417
    0.06
     TOUCH
    0.06
    ropa
    0.06
    ả
    0.06
    Activations Density 0.000%

    No Known Activations