© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 77386
    Prev
    Next
    INDEX
    Explanations

    terms related to news and media coverage

    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
    usher
    -0.08
    oe
    -0.07
    less
    -0.07
    kel
    -0.07
    uzzi
    -0.07
    ige
    -0.06
    lassen
    -0.06
    lass
    -0.06
    esimal
    -0.06
     Levine
    -0.06
    POSITIVE LOGITS
    âĸį
    0.08
    IBC
    0.08
    edith
    0.07
    æľ¯
    0.07
    polator
    0.07
    RTL
    0.07
    ogue
    0.07
    ãĤ¦ãĥĪ
    0.06
    inflate
    0.06
     unr
    0.06
    Activations Density 0.531%

    No Known Activations