© 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. 28969
    Prev
    Next
    INDEX
    Explanations

    discussions about copyright and voluntary content sharing

    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
    adal
    -0.07
    oe
    -0.06
    425
    -0.06
    529
    -0.06
    arb
    -0.06
    å±ŀ
    -0.06
    482
    -0.06
    iph
    -0.06
    SEG
    -0.06
    240
    -0.06
    POSITIVE LOGITS
    tpl
    0.07
    /REC
    0.07
    antic
    0.07
    ãĥįãĥ«
    0.07
    geç
    0.07
    .getDocument
    0.06
    OWNER
    0.06
    afil
    0.06
    vlc
    0.06
     ìĨĮ리
    0.06
    Activations Density 0.003%

    No Known Activations