© 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. 125337
    Prev
    Next
    INDEX
    Explanations

    mentions of figures and illustrations in a document

    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
     Thumb
    -0.06
    iyat
    -0.06
    omencl
    -0.06
    ofday
    -0.06
    quette
    -0.06
     VÅ¡ech
    -0.06
    ronics
    -0.06
    ianne
    -0.06
    ither
    -0.06
    etros
    -0.06
    POSITIVE LOGITS
    rew
    0.07
    akis
    0.07
     hol
    0.07
    зем
    0.06
    же
    0.06
     Fuller
    0.06
    ohl
    0.06
    лаж
    0.06
    _compat
    0.06
    iske
    0.06
    Activations Density 0.039%

    No Known Activations