© 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. 15-LLAMASCOPE-RES-131K
    11. 90034
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude or requests for help

    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
    ka
    -0.07
     Inner
    -0.07
    is
    -0.06
    bol
    -0.06
    ãĥ³ãĤ¹
    -0.06
    unny
    -0.06
    jud
    -0.06
    _gateway
    -0.06
    est
    -0.05
    .pa
    -0.05
    POSITIVE LOGITS
    Uvs
    0.08
    é§ħå¾ĴæŃ©
    0.07
    adero
    0.07
    Ïģή
    0.07
    reeze
    0.07
    BorderStyle
    0.07
    odash
    0.07
    oire
    0.07
    wear
    0.07
    AppComponent
    0.07
    Activations Density 0.001%

    No Known Activations