© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 58847
    Prev
    Next
    INDEX
    Explanations

    conjunctions and their repeated usage in various contexts

    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
    _exempt
    -0.06
    ourn
    -0.06
    theless
    -0.05
    iov
    -0.05
    uil
    -0.05
    gnu
    -0.05
     choke
    -0.05
    emi
    -0.05
    )((((
    -0.05
    elia
    -0.05
    POSITIVE LOGITS
    #ad
    0.07
    astics
    0.07
    γεν
    0.07
     Hindered
    0.07
    /or
    0.07
    격
    0.07
    μεν
    0.07
    rost
    0.07
    uba
    0.06
    .flash
    0.06
    Activations Density 0.038%

    No Known Activations