© 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. 57370
    Prev
    Next
    INDEX
    Explanations

    occurrences of the verbs "have" and "has" in various forms

    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
     underwent
    -0.09
    onth
    -0.08
    aho
    -0.07
    oubted
    -0.06
     VÅ¡ech
    -0.06
    ific
    -0.06
    acious
    -0.06
    otr
    -0.06
    оÑĢм
    -0.06
    ŀæĢ§
    -0.06
    POSITIVE LOGITS
     been
    0.17
    htag
    0.13
    been
    0.12
    nt
    0.11
     Been
    0.11
     sido
    0.11
     become
    0.10
    Been
    0.10
    htable
    0.10
     BEEN
    0.10
    Activations Density 0.597%

    No Known Activations