© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 75903
    Prev
    Next
    INDEX
    Explanations

    phrases related to customer satisfaction and positive experiences

    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
     |
    -0.06
    ulp
    -0.06
     --
    -0.06
    olean
    -0.06
    lsa
    -0.06
    ,
    -0.06
     homes
    -0.05
    деÑĤ
    -0.05
     +
    -0.05
     school
    -0.05
    POSITIVE LOGITS
    Ñģо
    0.08
    WithType
    0.07
    ÐĶÐļ
    0.07
    Servers
    0.07
    vern
    0.07
    Ñĸдом
    0.07
    елÑİ
    0.07
     Midi
    0.07
    Monad
    0.07
    ве
    0.07
    Activations Density 0.000%

    No Known Activations