© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 118948
    Prev
    Next
    INDEX
    Explanations

    different forms of expression and representation in various contexts

    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
    mul
    -0.07
    okit
    -0.07
    _PATCH
    -0.07
    ÑĢаÑģÑĤ
    -0.07
    ãĥ¼ãĥĭ
    -0.07
     Cobb
    -0.07
    аниÑĨ
    -0.07
    ahn
    -0.07
    amentals
    -0.07
    nger
    -0.07
    POSITIVE LOGITS
    Į¨
    0.06
    alink
    0.06
    /form
    0.06
     addCriterion
    0.06
    /modal
    0.06
    Rnd
    0.06
    adal
    0.05
     Legislature
    0.05
    TabPage
    0.05
    æѦ
    0.05
    Activations Density 0.047%

    No Known Activations