© 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. 78825
    Prev
    Next
    INDEX
    Explanations

    terms associated with trademarks and logos

    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
    uble
    -0.08
    scribe
    -0.07
    eras
    -0.07
    ingen
    -0.07
    ajas
    -0.06
    Facade
    -0.06
    ạo
    -0.06
     SPDX
    -0.06
    exas
    -0.06
     pé
    -0.06
    POSITIVE LOGITS
     Bren
    0.06
    agini
    0.06
    ONS
    0.06
    ="../../../
    0.06
    ETERS
    0.06
    oe
    0.06
    oppers
    0.06
    گاÙĨ
    0.06
    lices
    0.06
    /Framework
    0.05
    Activations Density 0.001%

    No Known Activations