© 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. 61753
    Prev
    Next
    INDEX
    Explanations

    phrases indicating duality or comparison between two entities

    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
    airo
    -0.06
    ÑĨев
    -0.06
    Ïĥε
    -0.06
    achte
    -0.06
    oken
    -0.06
    abad
    -0.06
    lin
    -0.06
    à¤Łà¤°
    -0.06
    ç´ł
    -0.06
    occo
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.07
    /or
    0.07
    iets
    0.07
    ikat
    0.07
     sexes
    0.07
     Böl
    0.07
    zeit
    0.06
    mailer
    0.06
    iffe
    0.06
    _definitions
    0.06
    Activations Density 0.010%

    No Known Activations