© 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. 128757
    Prev
    Next
    INDEX
    Explanations

    modal verbs and phrases indicating requests or actions to be taken

    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
    rimon
    -0.08
    attery
    -0.08
    Ø®Ùħ
    -0.08
    NOP
    -0.07
    riba
    -0.07
    [js
    -0.07
    Multiply
    -0.07
    ɵ
    -0.07
    خت
    -0.07
    hausen
    -0.07
    POSITIVE LOGITS
    esh
    0.07
    ju
    0.07
    imat
    0.06
    ä¸įè¦ģ
    0.06
     consider
    0.06
     adopt
    0.06
     include
    0.06
    ogui
    0.06
     consideration
    0.06
     shouldn
    0.06
    Activations Density 0.018%

    No Known Activations