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. 61024
    Prev
    Next
    INDEX
    Explanations

    phrases indicating quantity or presence

    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
    æĪĸ
    -0.08
    ãģ¾ãģļ
    -0.08
     еÑģÑĤе
    -0.08
    æĪĸèĢħ
    -0.07
     or
    -0.07
     nebo
    -0.07
    ìĿ´ëĤĺ
    -0.07
     или
    -0.07
    mÃŃ
    -0.07
     æĪĸ
    -0.07
    POSITIVE LOGITS
     alike
    0.12
     depending
    0.10
    /etc
    0.09
    depending
    0.09
     of
    0.07
    eway
    0.06
    ota
    0.06
     respectively
    0.06
    sic
    0.06
     Universal
    0.06
    Activations Density 0.014%

    No Known Activations