© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 94365
    Prev
    Next
    INDEX
    Explanations

    mentions of information and its availability

    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
    alk
    -0.07
    ken
    -0.07
    .AF
    -0.07
    atak
    -0.07
    quia
    -0.06
    oria
    -0.06
    uki
    -0.06
     mush
    -0.06
    urch
    -0.06
    æīĢæľī
    -0.06
    POSITIVE LOGITS
     than
    0.13
    than
    0.11
    -than
    0.11
    _than
    0.11
     THAN
    0.10
     Than
    0.10
    Than
    0.09
     about
    0.08
     niż
    0.07
     än
    0.07
    Activations Density 0.012%

    No Known Activations