© 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. 118376
    Prev
    Next
    INDEX
    Explanations

    statements of acknowledgment and admission regarding situations

    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
    odable
    -0.08
    _JS
    -0.08
    ÌĨ
    -0.08
    ¶Į
    -0.07
    oog
    -0.07
     Dün
    -0.07
    iosper
    -0.07
    .SYSTEM
    -0.07
    ãĥ©ãĤ¤ãĥ³
    -0.07
    estone
    -0.07
    POSITIVE LOGITS
     sometimes
    0.10
     occasionally
    0.10
    inde
    0.09
     Sometimes
    0.08
    Sometimes
    0.08
    æľīäºĽ
    0.07
     indeed
    0.07
     yes
    0.07
     somewhat
    0.07
     initially
    0.07
    Activations Density 0.027%

    No Known Activations