© 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. 17-LLAMASCOPE-RES-131K
    11. 61352
    Prev
    Next
    INDEX
    Explanations

    references to specific numerical values or identifiers in a formal 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
    ters
    -0.08
    rema
    -0.07
    geh
    -0.07
    istani
    -0.07
    yu
    -0.07
    ting
    -0.07
    atrib
    -0.07
    /pass
    -0.07
    isposable
    -0.07
    pend
    -0.07
    POSITIVE LOGITS
    ovnÄĽ
    0.07
    th
    0.07
    orthy
    0.07
    ouns
    0.07
    igh
    0.07
    ousel
    0.07
    ly
    0.06
    ĶåĽŀ
    0.06
    į
    0.06
    IGH
    0.06
    Activations Density 0.030%

    No Known Activations