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

    Neuronpedia

    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. 17-LLAMASCOPE-RES-131K
    11. 84971
    Prev
    Next
    INDEX
    Explanations

    processes and methodologies related to manufacturing or technical specifications

    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
    y
    -0.08
    ties
    -0.07
    ies
    -0.06
    u
    -0.06
    oning
    -0.06
    h
    -0.06
     stated
    -0.06
     Alma
    -0.06
    t
    -0.06
     McB
    -0.06
    POSITIVE LOGITS
    nech
    0.07
     FetchType
    0.07
    ;amp
    0.07
    olec
    0.07
    %%%%%%%%%%%%%%%%
    0.07
     ele
    0.07
    ầm
    0.07
    å§ĵ
    0.07
    alam
    0.07
    ControlEvents
    0.07
    Activations Density 0.000%

    No Known Activations