© 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. 93637
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate numerical ranges or limits

    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
     McCart
    -0.07
     IMS
    -0.07
    bare
    -0.06
    éIJĺ
    -0.06
    çľ¾
    -0.06
    esses
    -0.06
    una
    -0.06
    ha
    -0.06
    elp
    -0.06
    .MM
    -0.06
    POSITIVE LOGITS
    Including
    0.08
     till
    0.07
    iveau
    0.07
     beyond
    0.07
     inclusive
    0.07
     including
    0.07
     until
    0.07
    /down
    0.07
    chas
    0.07
     Till
    0.06
    Activations Density 0.020%

    No Known Activations