© 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. 106418
    Prev
    Next
    INDEX
    Explanations

    comparisons and analogies related to concepts and restrictions

    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
    sis
    -0.07
    azine
    -0.07
    iben
    -0.07
    opath
    -0.07
    .bukkit
    -0.07
    imen
    -0.07
     اÙĦÙĪ
    -0.07
    inh
    -0.06
    .mdl
    -0.06
    ses
    -0.06
    POSITIVE LOGITS
     other
    0.12
    other
    0.08
     otras
    0.08
     anderen
    0.07
    åħ¶ä»ĸ
    0.07
    ãģĿãģ®ä»ĸ
    0.07
     altre
    0.07
     autres
    0.07
    (other
    0.07
     ساÛĮر
    0.07
    Activations Density 0.036%

    No Known Activations