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

    Neuronpedia

    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. 4314
    Prev
    Next
    INDEX
    Explanations

    the verb "do" and its variations, indicating actions being performed

    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
    redd
    -0.07
    pher
    -0.07
    pery
    -0.07
    hurst
    -0.07
    cular
    -0.07
    rous
    -0.07
    rett
    -0.07
    edi
    -0.07
    pret
    -0.07
    meer
    -0.06
    POSITIVE LOGITS
    cket
    0.11
    ctest
    0.09
     justice
    0.08
    ctr
    0.08
    ork
    0.08
    actic
    0.08
     away
    0.08
    ctors
    0.08
    ña
    0.08
    ctype
    0.07
    Activations Density 0.168%

    No Known Activations