© 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. 40741
    Prev
    Next
    INDEX
    Explanations

    references to categorization labels or tags

    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
    alice
    -0.07
    wner
    -0.07
     воÑĤ
    -0.07
    kos
    -0.06
    ringe
    -0.06
    OTT
    -0.06
    Å¡t
    -0.06
    unsch
    -0.06
    osg
    -0.06
    umeric
    -0.06
    POSITIVE LOGITS
    ITO
    0.06
     prot
    0.06
    ãĥ
    0.06
    ksen
    0.06
    omba
    0.05
     pragma
    0.05
     Bad
    0.05
    timing
    0.05
    756
    0.05
    èĩ
    0.05
    Activations Density 0.001%

    No Known Activations