© 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. 118959
    Prev
    Next
    INDEX
    Explanations

    phrases indicating customer service and assistance

    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
    atts
    -0.07
     c
    -0.06
     f
    -0.06
    berger
    -0.06
    ajan
    -0.05
    ens
    -0.05
     
    -0.05
     blank
    -0.05
    eb
    -0.05
    -
    -0.05
    POSITIVE LOGITS
     addCriterion
    0.09
    uras
    0.08
    á»ĵng
    0.08
    conde
    0.08
    -Identifier
    0.08
    اÛĮØ´
    0.08
    AllowAnonymous
    0.08
    EdgeInsets
    0.07
     ÑĤабли
    0.07
    ãĤ©
    0.07
    Activations Density 0.031%

    No Known Activations