© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 28579
    Prev
    Next
    INDEX
    Explanations

    references to mobile phone features and specifications

    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
    enso
    -0.08
     tane
    -0.07
    çħĻ
    -0.07
    abox
    -0.07
    blo
    -0.07
    rowsable
    -0.07
    svp
    -0.07
    FETCH
    -0.07
    xbe
    -0.07
    ContentPane
    -0.06
    POSITIVE LOGITS
     voice
    0.08
     calls
    0.08
     conversations
    0.07
     call
    0.07
     phone
    0.07
     ear
    0.07
    çĶµè¯Ŀ
    0.07
     Voice
    0.07
     speech
    0.07
     talking
    0.07
    Activations Density 0.144%

    No Known Activations