© 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. 83999
    Prev
    Next
    INDEX
    Explanations

    technical terms and parameters related to software and network configurations

    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
    imler
    -0.10
    ekil
    -0.10
    rupa
    -0.10
    vek
    -0.09
    upal
    -0.09
    Multiplicity
    -0.09
    UNUSED
    -0.09
    _oauth
    -0.08
    обов
    -0.08
    &uuml
    -0.08
    POSITIVE LOGITS
     policy
    0.08
     setting
    0.07
     mode
    0.07
     off
    0.07
     Policy
    0.07
    Mode
    0.07
     false
    0.06
     Mode
    0.06
     turned
    0.06
     option
    0.06
    Activations Density 0.033%

    No Known Activations