© 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. 17-LLAMASCOPE-RES-131K
    11. 28711
    Prev
    Next
    INDEX
    Explanations

    the repeated use of the verb "do" 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
    not
    -0.08
     not
    -0.07
    rawn
    -0.07
    iegel
    -0.07
    nid
    -0.07
     indeed
    -0.06
    doch
    -0.06
    nt
    -0.06
    ras
    -0.06
    anse
    -0.06
    POSITIVE LOGITS
    imde
    0.09
    stride
    0.06
    532
    0.06
    athi
    0.06
    ardi
    0.06
    jer
    0.06
    áÅĻ
    0.06
    agua
    0.06
    ostream
    0.06
    <const
    0.06
    Activations Density 0.035%

    No Known Activations