© 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. 5-LLAMASCOPE-RES-131K
    11. 126085
    Prev
    Next
    INDEX
    Explanations

    references to Netflix and its content

    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
     Dew
    -0.07
    adol
    -0.07
    ucci
    -0.07
    eldon
    -0.06
    ç¤
    -0.06
    alo
    -0.06
     Kou
    -0.06
    _ATOM
    -0.06
    ssf
    -0.06
    het
    -0.06
    POSITIVE LOGITS
    ENTA
    0.08
    ÑĥÑģа
    0.07
    nah
    0.07
    StackNavigator
    0.06
    AGMA
    0.06
    ICES
    0.06
    ede
    0.06
    ιÏİν
    0.06
    inka
    0.06
    ijn
    0.06
    Activations Density 0.003%

    No Known Activations