© 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. 5-LLAMASCOPE-RES-131K
    11. 126070
    Prev
    Next
    INDEX
    Explanations

    the word "many" 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
    792
    -0.07
    mates
    -0.07
     hann
    -0.06
    irie
    -0.06
     Bow
    -0.06
    noop
    -0.06
    avou
    -0.06
    ful
    -0.06
    sites
    -0.06
    lings
    -0.06
    POSITIVE LOGITS
    ãģķãģ¾
    0.07
    eno
    0.07
    ìĪ
    0.07
    urum
    0.06
    umba
    0.06
    /*================================================================
    0.06
    ÏĨα
    0.06
    ala
    0.06
    ãĥĥãĥĦ
    0.06
    ÑĨик
    0.06
    Activations Density 0.041%

    No Known Activations