© 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. 125365
    Prev
    Next
    INDEX
    Explanations

    references to self-improvement or self-reliance

    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
    izards
    -0.07
    iyah
    -0.07
    #End
    -0.06
    ablish
    -0.06
     Sala
    -0.06
    fast
    -0.06
    ardown
    -0.06
    regor
    -0.06
     predic
    -0.06
    vem
    -0.06
    POSITIVE LOGITS
    CTS
    0.07
    ronic
    0.06
    /mock
    0.06
    ledge
    0.06
    غة
    0.06
    ammer
    0.06
     anth
    0.06
    343
    0.06
     Howe
    0.06
     Tou
    0.06
    Activations Density 0.000%

    No Known Activations