© 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. 94017
    Prev
    Next
    INDEX
    Explanations

    references to data and resource management

    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
    &q
    -0.06
    .Xaml
    -0.06
    vens
    -0.06
     Fame
    -0.06
     pragma
    -0.05
     McCorm
    -0.05
     Chambers
    -0.05
    indi
    -0.05
    олÑĮз
    -0.05
    ominated
    -0.05
    POSITIVE LOGITS
     dikke
    0.08
    igsaw
    0.07
    byn
    0.07
    aterangepicker
    0.07
    ../../../
    0.07
    uraa
    0.07
    ksam
    0.06
    ahoo
    0.06
    izzato
    0.06
    imest
    0.06
    Activations Density 0.002%

    No Known Activations