© 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. 61212
    Prev
    Next
    INDEX
    Explanations

    specific numeric references, such as page numbers or volume and issue numbers in academic journals

    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
    :
    -0.06
    ould
    -0.06
    -↵
    -0.06
     lip
    -0.06
    dit
    -0.06
    ,↵
    -0.05
    émon
    -0.05
     Dip
    -0.05
    !
    -0.05
    ines
    -0.05
    POSITIVE LOGITS
    WidgetItem
    0.08
    jie
    0.08
    ixa
    0.07
    odka
    0.07
    .cy
    0.07
    Ø®ÙĪ
    0.07
    çIJ
    0.07
    ãĥ³ãĥij
    0.07
    defgroup
    0.07
    odox
    0.07
    Activations Density 0.003%

    No Known Activations