© 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. 17-LLAMASCOPE-RES-131K
    6. 84561
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical characteristics and attributes of dogs

    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
    867
    -0.07
     cater
    -0.07
    ulet
    -0.07
    670
    -0.07
    urette
    -0.07
    ieux
    -0.07
    467
    -0.07
    _proba
    -0.07
     HOST
    -0.06
    peak
    -0.06
    POSITIVE LOGITS
    irus
    0.07
    iltr
    0.06
    ingle
    0.06
    ili
    0.06
    anst
    0.06
    arLayout
    0.06
     ter
    0.06
    \Url
    0.06
     preferably
    0.06
    canvas
    0.06
    Activations Density 0.005%

    No Known Activations