© 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. 76262
    Prev
    Next
    INDEX
    Explanations

    phrases indicating structural changes or deterioration

    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
     erotik
    -0.08
    biz
    -0.07
    wart
    -0.06
     dig
    -0.06
    176
    -0.06
    ember
    -0.06
     worldwide
    -0.06
    enberg
    -0.06
     relevant
    -0.06
     documentos
    -0.06
    POSITIVE LOGITS
    upy
    0.09
     è¢
    0.07
    uby
    0.07
    hek
    0.07
    hone
    0.07
    asion
    0.07
    LOAT
    0.07
    rend
    0.07
    ĮĢ
    0.07
    oa
    0.06
    Activations Density 0.000%

    No Known Activations