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. 96292
    Prev
    Next
    INDEX
    Explanations

    references to terms and conditions related to website usage

    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
    ,
    -0.07
     or
    -0.06
    is
    -0.06
     as
    -0.06
     Cr
    -0.06
     and
    -0.06
     supposed
    -0.06
     (
    -0.06
     R
    -0.06
    eds
    -0.06
    POSITIVE LOGITS
    imdi
    0.10
    áž
    0.10
    erah
    0.09
    .nano
    0.09
    baugh
    0.09
    âĢĮد
    0.09
    acific
    0.09
    emale
    0.09
    endon
    0.09
    edata
    0.08
    Activations Density 0.002%

    No Known Activations