Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 44165
    Prev
    Next
    INDEX
    Explanations

    mentions of the location "Dundee."

    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
    ÑĤÑĢ
    -0.07
    ξη
    -0.07
    LETTE
    -0.07
    ÑģÑĤÑĢ
    -0.06
    BERS
    -0.06
    interrupt
    -0.06
    SEL
    -0.06
     Nu
    -0.06
    istra
    -0.05
     habitual
    -0.05
    POSITIVE LOGITS
    ee
    0.17
    onald
    0.15
    alk
    0.12
    rum
    0.10
    onian
    0.10
    ees
    0.10
     ee
    0.09
    onn
    0.09
    eee
    0.09
    eeee
    0.09
    Activations Density 0.001%

    No Known Activations