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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 88278
    Prev
    Next
    INDEX
    Explanations

    keywords related to official document citations and references

    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
    ments
    -0.06
    oretical
    -0.06
     wr
    -0.05
    á»įn
    -0.05
    jd
    -0.05
    ons
    -0.05
    ober
    -0.05
     eventual
    -0.05
    aki
    -0.05
    ибли
    -0.05
    POSITIVE LOGITS
    ritel
    0.07
    нима
    0.07
     Copyright
    0.07
    adele
    0.07
    åľŃ
    0.07
    (æľ¨
    0.07
    _INTEGER
    0.07
    ascus
    0.07
    ì§ĢëıĦ
    0.07
    ÐĶÐļ
    0.07
    Activations Density 0.001%

    No Known Activations