Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 29384
    Prev
    Next
    INDEX
    Explanations

    instances of the word "by" indicating the agent or creator of the content

    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
     Wich
    -0.06
    ill
    -0.06
    амп
    -0.06
    ิลล
    -0.05
    ÑĤен
    -0.05
     among
    -0.05
    -era
    -0.05
     Quart
    -0.05
    etin
    -0.05
     group
    -0.05
    POSITIVE LOGITS
    /of
    0.09
    thew
    0.08
    unsch
    0.07
    VOICE
    0.07
    okane
    0.07
    ĵåIJį
    0.07
    PRESSION
    0.07
    oad
    0.07
    :
    0.07
    elik
    0.07
    Activations Density 0.009%

    No Known Activations