© 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. 106427
    Prev
    Next
    INDEX
    Explanations

    sections that contain statistical or factual information

    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
    æłª
    -0.08
    arch
    -0.06
    æĩ
    -0.06
    iles
    -0.06
    anning
    -0.06
    inta
    -0.06
    _highlight
    -0.06
    Paren
    -0.06
     Gall
    -0.06
    èŃ·
    -0.06
    POSITIVE LOGITS
    ighb
    0.07
     Rosenstein
    0.06
    ISTR
    0.06
    ¹Ħ
    0.06
    کرد
    0.06
    ighthouse
    0.06
    OID
    0.06
    ìį¨
    0.06
    issy
    0.06
    IOR
    0.06
    Activations Density 0.001%

    No Known Activations