© 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. 15-LLAMASCOPE-RES-131K
    11. 103687
    Prev
    Next
    INDEX
    Explanations

    calls to action for audience engagement

    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
    ubits
    -0.06
     Smy
    -0.06
    uir
    -0.06
    avis
    -0.06
     '&#
    -0.06
    DOMNode
    -0.06
    fte
    -0.05
     Papers
    -0.05
    ict
    -0.05
    ermen
    -0.05
    POSITIVE LOGITS
     Hindered
    0.08
     Berk
    0.07
     elsewhere
    0.07
    #
    0.07
    macen
    0.06
    }elseif
    0.06
    ienes
    0.06
    wel
    0.06
    opoulos
    0.06
    Tweet
    0.06
    Activations Density 0.005%

    No Known Activations