© 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. 2797
    Prev
    Next
    INDEX
    Explanations

    features related to footwear design and stability

    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
    etti
    -0.08
    flate
    -0.06
    ao
    -0.06
    onga
    -0.06
     ole
    -0.06
    furt
    -0.06
     Lif
    -0.05
    ix
    -0.05
    grund
    -0.05
     Mind
    -0.05
    POSITIVE LOGITS
    æľµ
    0.07
    -entry
    0.07
    ål
    0.07
    annel
    0.07
    iyon
    0.07
    ÅĤy
    0.07
    _VLAN
    0.07
    alloca
    0.07
    dbus
    0.07
    ervoir
    0.07
    Activations Density 0.010%

    No Known Activations