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. 43875
    Prev
    Next
    INDEX
    Explanations

    technical programming terms and concepts

    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
     RuntimeObject
    -0.07
     Void
    -0.06
    ascript
    -0.06
     RSS
    -0.06
     Herbert
    -0.06
    _void
    -0.06
     RN
    -0.06
    .Void
    -0.06
    void
    -0.06
    Void
    -0.06
    POSITIVE LOGITS
     DbSet
    0.12
     virtual
    0.12
     ICollection
    0.12
    virtual
    0.10
    ICollection
    0.10
     Nullable
    0.10
     ApplicationUser
    0.10
    VIRTUAL
    0.09
     modelBuilder
    0.09
     EF
    0.09
    Activations Density 0.006%

    No Known Activations