© 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. 82765
    Prev
    Next
    INDEX
    Explanations

    references to education and learning outcomes

    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
    verity
    -0.07
    lasses
    -0.07
    abee
    -0.07
    ernal
    -0.06
    assin
    -0.06
    omo
    -0.06
    ÃľM
    -0.06
    471
    -0.06
    áš
    -0.06
     Teach
    -0.06
    POSITIVE LOGITS
     understand
    0.08
     understanding
    0.07
     hopefully
    0.07
    Upon
    0.07
     ability
    0.06
     knowledge
    0.06
    ัà¸Ļà¹Ħà¸Ķ
    0.06
     Upon
    0.06
    ÙĨب
    0.06
     understands
    0.06
    Activations Density 0.016%

    No Known Activations