© 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. 61196
    Prev
    Next
    INDEX
    Explanations

    programming terminology and code elements

    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
    anta
    -0.06
    -prepend
    -0.06
     Slack
    -0.06
    zon
    -0.06
     mart
    -0.06
    fra
    -0.06
     McKin
    -0.05
     Latter
    -0.05
     Travis
    -0.05
    .baidu
    -0.05
    POSITIVE LOGITS
    anzeigen
    0.06
    ãģĵãĤĵãģ«
    0.06
    adir
    0.06
    اÙĬØ©
    0.06
     âĢı
    0.06
    ominated
    0.06
    bows
    0.06
    éĽĦ
    0.06
    caps
    0.06
    bens
    0.06
    Activations Density 0.032%

    No Known Activations