© 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. 106118
    Prev
    Next
    INDEX
    Explanations

    references to distinct episodes or events

    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
    rer
    -0.08
    xed
    -0.08
    land
    -0.07
    Ñij
    -0.07
    wart
    -0.07
    landers
    -0.07
    öl
    -0.07
    roe
    -0.07
    ãĥ¼ãĤ¹
    -0.07
    lander
    -0.07
    POSITIVE LOGITS
    ary
    0.07
    cle
    0.07
    ixon
    0.06
    onte
    0.06
    370
    0.06
    urum
    0.06
     Douglas
    0.06
    zia
    0.06
     éĸ
    0.06
     occasion
    0.06
    Activations Density 0.005%

    No Known Activations