© 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. 76965
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a request for additional information or clarification

    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
    oner
    -0.07
     funnel
    -0.06
    /s
    -0.06
    '
    -0.06
    esser
    -0.06
    linger
    -0.06
    onso
    -0.06
    avr
    -0.05
    -
    -0.05
    _
    -0.05
    POSITIVE LOGITS
    #ga
    0.09
    .scalablytyped
    0.09
    rias
    0.08
    ãĥ³ãĥĨ
    0.08
     ÑģмоÑĤ
    0.08
    <source
    0.07
    ãģıãĤī
    0.07
     millenn
    0.07
    adero
    0.07
    otec
    0.07
    Activations Density 0.000%

    No Known Activations