© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 3286
    Prev
    Next
    INDEX
    Explanations

    HTML tags and elements typically used in web page titles and headings

    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
    ãĤ
    -0.07
    VID
    -0.07
    arty
    -0.06
    Ñľ
    -0.06
    ues
    -0.06
    æģµ
    -0.06
     Buen
    -0.06
    ovat
    -0.06
     Cue
    -0.06
    ẻ
    -0.06
    POSITIVE LOGITS
    ãĥ¼ãĥł
    0.07
    yh
    0.06
    aye
    0.06
    edn
    0.06
    Tit
    0.06
    needle
    0.06
    shaw
    0.06
     Tit
    0.06
     isConnected
    0.06
     tit
    0.06
    Activations Density 0.003%

    No Known Activations