© 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. 84178
    Prev
    Next
    INDEX
    Explanations

    references to events or decisions related to leadership and authority

    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
    uhan
    -0.08
     optionally
    -0.07
    seau
    -0.07
    pires
    -0.07
    otec
    -0.07
    -нибÑĥдÑĮ
    -0.06
    AYER
    -0.06
     hopefully
    -0.06
    каж
    -0.06
    _seek
    -0.06
    POSITIVE LOGITS
     instead
    0.15
    instead
    0.13
     Instead
    0.13
    Instead
    0.12
     ultimately
    0.10
     eventual
    0.09
     вмеÑģÑĤ
    0.08
     eventually
    0.08
     Ultimately
    0.07
     elsewhere
    0.07
    Activations Density 0.021%

    No Known Activations