© 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. 71373
    Prev
    Next
    INDEX
    Explanations

     phrases emphasizing attempts and efforts to make positive changes or improvements

    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
    ια
    -0.07
    ROUT
    -0.07
    ouve
    -0.06
    iggins
    -0.06
    action
    -0.06
     radix
    -0.06
     Verfügung
    -0.06
    èĬ
    -0.05
     travail
    -0.05
     action
    -0.05
    POSITIVE LOGITS
     to
    0.10
     towards
    0.08
    uš
    0.07
     ÑĩÑĤобÑĭ
    0.07
     toward
    0.07
     να
    0.07
    нÑĸÑĪ
    0.06
    ToOne
    0.06
    .Abstractions
    0.06
     Äijá»ĥ
    0.06
    Activations Density 0.018%

    No Known Activations