© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 789
    Prev
    Next
    INDEX
    Explanations

    references to construction and infrastructure maintenance details

    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
    lobs
    -0.07
    639
    -0.07
     corpor
    -0.06
    aname
    -0.06
     Barr
    -0.06
     stalls
    -0.06
    steps
    -0.06
    avana
    -0.06
     typeid
    -0.06
     Porter
    -0.06
    POSITIVE LOGITS
     underground
    0.07
    ivec
    0.07
     backbone
    0.07
    okrat
    0.06
    _LEG
    0.06
    èĽĩ
    0.06
     Äijoạn
    0.06
    osit
    0.06
     STREET
    0.06
    izen
    0.06
    Activations Density 0.009%

    No Known Activations