© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 794
    Prev
    Next
    INDEX
    Explanations

    references to programming libraries or collections in a technical context

    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
    dsl
    -0.07
    meld
    -0.07
    steder
    -0.07
    ]|[
    -0.07
    tgl
    -0.07
    dsn
    -0.07
    NIL
    -0.07
    autoload
    -0.06
    612
    -0.06
    ivatel
    -0.06
    POSITIVE LOGITS
     to
    0.06
    ing
    0.06
    FD
    0.06
     rem
    0.06
    uff
    0.06
    ãĥĥ
    0.06
    strand
    0.06
    _unpack
    0.06
     Kum
    0.05
     fence
    0.05
    Activations Density 0.000%

    No Known Activations