© 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. 61999
    Prev
    Next
    INDEX
    Explanations

    information related to specific characteristics or properties of objects or subjects

    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
    illet
    -0.07
    icus
    -0.07
    zilla
    -0.06
    ako
    -0.06
    our
    -0.06
    ages
    -0.06
    oy
    -0.05
    rod
    -0.05
    etter
    -0.05
    ISCO
    -0.05
    POSITIVE LOGITS
     ones
    0.15
    ones
    0.09
     Ones
    0.09
    ä¹ĭä¸Ģ
    0.07
    åħ¶ä¸Ń
    0.07
    usra
    0.07
     ranks
    0.07
    ATAL
    0.07
    tea
    0.07
    gree
    0.06
    Activations Density 0.010%

    No Known Activations