© 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. 55951
    Prev
    Next
    INDEX
    Explanations

    numerical data related to statistics and percentages

    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
    odied
    -0.08
    inality
    -0.07
    aste
    -0.07
    alk
    -0.07
     Butterfly
    -0.06
     Seal
    -0.06
     Catalyst
    -0.06
    æ°Ĺ
    -0.06
    ulu
    -0.06
    ifest
    -0.06
    POSITIVE LOGITS
    normal
    0.07
    olini
    0.06
    loh
    0.06
    -normal
    0.06
    essim
    0.06
    aison
    0.06
    ãĥ¼ãĥĩ
    0.06
     normal
    0.06
    æŃ£å¸¸
    0.06
     voks
    0.06
    Activations Density 0.001%

    No Known Activations