© 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. 71534
    Prev
    Next
    INDEX
    Explanations

    punctuation marks or symbols indicating separation

    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
    901
    -0.07
    æĿ
    -0.07
    SizeMode
    -0.07
    çŃĨ
    -0.06
    quals
    -0.06
    errer
    -0.06
    levator
    -0.06
    xec
    -0.06
    uns
    -0.06
    ziej
    -0.06
    POSITIVE LOGITS
    elin
    0.07
    ãĥ¬ãĥ¼
    0.06
    uin
    0.06
     defaultMessage
    0.06
    ноп
    0.06
    θοÏĤ
    0.06
    uite
    0.06
     Morse
    0.06
    ily
    0.06
    éģĭåĭķ
    0.06
    Activations Density 0.000%

    No Known Activations