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. 43962
    Prev
    Next
    INDEX
    Explanations

    references to educational institutions and academic publications

    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
    apol
    -0.08
    -INF
    -0.08
    apse
    -0.07
    úsqueda
    -0.07
    TEGER
    -0.07
    ozÃŃ
    -0.07
    isposable
    -0.07
    PCP
    -0.07
    indle
    -0.07
    arez
    -0.07
    POSITIVE LOGITS
     Gus
    0.10
     Maid
    0.10
     Abe
    0.10
     Dut
    0.09
     Jos
    0.08
     Yen
    0.08
     Min
    0.08
     Bir
    0.08
     Il
    0.08
     Port
    0.08
    Activations Density 0.010%

    No Known Activations