© 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. 16843
    Prev
    Next
    INDEX
    Explanations

    key metrics related to data usage and internet access

    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
    __
    -0.07
    Ñıл
    -0.06
    ~
    -0.06
    веÑģÑĤ
    -0.06
    YZ
    -0.05
    акÑģ
    -0.05
     mise
    -0.05
     Gun
    -0.05
     guise
    -0.05
    ŃĶ
    -0.05
    POSITIVE LOGITS
     MetroFramework
    0.08
    ruba
    0.08
    иÑģÑĤÑĢа
    0.08
    utterstock
    0.08
    innacle
    0.07
    urum
    0.07
    iaux
    0.07
    itchens
    0.07
    aeda
    0.07
    regon
    0.07
    Activations Density 0.013%

    No Known Activations