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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-LLAMASCOPE-RES-131K
    6. 96021
    Prev
    Next
    INDEX
    Explanations

    references to artistic productions and community events

    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
    ods
    -0.07
    elsey
    -0.06
    rik
    -0.05
    272
    -0.05
    mite
    -0.05
     Pal
    -0.05
     Vys
    -0.05
    allet
    -0.05
    zept
    -0.05
    235
    -0.05
    POSITIVE LOGITS
     respectively
    0.10
     respective
    0.09
     chac
    0.08
    åĪĨåĪ«
    0.07
    ['__
    0.07
    anie
    0.07
    änd
    0.07
    हर
    0.06
    ÑıÑģ
    0.06
    erdale
    0.06
    Activations Density 0.189%

    No Known Activations