© 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. 125812
    Prev
    Next
    INDEX
    Explanations

    references to prominent individuals and their actions or statements

    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
    VERRIDE
    -0.07
    çĶ
    -0.07
    alc
    -0.06
    _DBG
    -0.06
     Replies
    -0.06
    ä¸ĭ载次æķ°
    -0.06
    Ñĩай
    -0.06
    ä¸ŃæĸĩåŃĹå¹ķ
    -0.06
    éĺħ读次æķ°
    -0.06
    Äįka
    -0.06
    POSITIVE LOGITS
     statement
    0.08
     speaking
    0.07
    ãĤ¤ãĤº
    0.07
     mention
    0.07
     sentiment
    0.07
    _globals
    0.06
    vider
    0.06
     statements
    0.06
     further
    0.06
     thereby
    0.06
    Activations Density 0.051%

    No Known Activations