© 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. 129017
    Prev
    Next
    INDEX
    Explanations

    hexadecimal color codes

    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
    aska
    -0.08
    986
    -0.07
    oden
    -0.07
    inou
    -0.07
    levation
    -0.06
    umba
    -0.06
    _taxonomy
    -0.06
    ispiel
    -0.06
    989
    -0.06
     Carl
    -0.06
    POSITIVE LOGITS
    lrt
    0.07
    ONGL
    0.07
    ÙĪاÙĦ
    0.07
    .tie
    0.06
    ADC
    0.06
    vil
    0.06
    даÑĤ
    0.06
    ÑĮко
    0.06
    #ad
    0.06
    inded
    0.06
    Activations Density 0.004%

    No Known Activations