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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5199
    Prev
    Next
    INDEX
    Explanations

    indications of limitations or specific conditions in contexts involving choice or requirements

    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
    sher
    -0.08
    ollen
    -0.07
    icken
    -0.07
    abei
    -0.07
    wich
    -0.07
     ÑĩÑĥж
    -0.07
    atsu
    -0.07
    žil
    -0.07
    á»ĩ
    -0.07
     вÑģÑİ
    -0.07
    POSITIVE LOGITS
     mere
    0.13
     just
    0.10
     merely
    0.09
     fewer
    0.09
     handful
    0.09
     single
    0.09
     nothing
    0.09
     manageable
    0.09
    mere
    0.08
     less
    0.08
    Activations Density 0.025%

    No Known Activations