© 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. 27264
    Prev
    Next
    INDEX
    Explanations

    expressions of physical capability and personal anecdotes

    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
    ">//
    -0.08
    auer
    -0.07
    "\↵
    -0.07
    ÌĨ
    -0.07
    丸
    -0.07
     ÑĤÑĢанÑģп
    -0.07
    ãĥĥãĥĹ
    -0.07
    ÑĤÑĢа
    -0.07
     Göz
    -0.07
    ials
    -0.07
    POSITIVE LOGITS
     Forces
    0.06
    odon
    0.05
    0.05
    ynes
    0.05
     Ment
    0.05
     Meredith
    0.05
    ayar
    0.05
     Reese
    0.05
    ,strong
    0.05
    oleon
    0.05
    Activations Density 0.024%

    No Known Activations