© 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. 26826
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical issues and system errors

    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
     contracting
    -0.06
    æŁĦ
    -0.06
     Fist
    -0.06
     pol
    -0.06
     Reverse
    -0.06
    /Graphics
    -0.06
     Dise
    -0.06
    hlen
    -0.05
     Unlimited
    -0.05
     Anal
    -0.05
    POSITIVE LOGITS
     same
    0.10
    Same
    0.09
    same
    0.09
    _same
    0.08
    erville
    0.08
     still
    0.08
    orf
    0.07
     Same
    0.07
     ëĺ
    0.07
     identical
    0.07
    Activations Density 0.008%

    No Known Activations