© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 76813
    Prev
    Next
    INDEX
    Explanations

    details related to film production credits and music elements

    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
    entai
    -0.09
    tember
    -0.08
    edback
    -0.07
    imli
    -0.07
    ambi
    -0.07
    rek
    -0.07
    zag
    -0.07
    .Mutable
    -0.07
    ombo
    -0.07
    #__
    -0.07
    POSITIVE LOGITS
     :
    0.07
     :↵
    0.06
    ges
    0.06
    вод
    0.06
     bathing
    0.05
    ons
    0.05
     Vin
    0.05
     Ramsey
    0.05
     |
    0.05
     ï¼ļ
    0.05
    Activations Density 0.001%

    No Known Activations