Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 84381
    Prev
    Next
    INDEX
    Explanations

    discussions about educational encouragement and student initiative

    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
    amespace
    -0.09
     seins
    -0.08
    Äħż
    -0.08
    erdale
    -0.08
    Intersection
    -0.08
    enido
    -0.08
    ipc
    -0.07
    resher
    -0.07
    oux
    -0.07
    _CF
    -0.07
    POSITIVE LOGITS
     elsewhere
    0.14
     other
    0.12
     alternative
    0.10
     another
    0.10
     alternatives
    0.10
     switch
    0.09
     Other
    0.09
     rival
    0.09
    other
    0.09
     competing
    0.09
    Activations Density 0.032%

    No Known Activations