© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 1958
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a negative sentiment or condition

    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
     Ventures
    -0.06
    kv
    -0.06
     fore
    -0.06
    528
    -0.06
    thur
    -0.06
     Stats
    -0.06
    ÂŃt
    -0.06
     bounced
    -0.06
     Onion
    -0.05
    alık
    -0.05
    POSITIVE LOGITS
    æŁ´
    0.07
    же
    0.07
    argar
    0.07
     earnings
    0.07
    amo
    0.07
    еÑĢÑĤ
    0.06
    baar
    0.06
     biên
    0.06
    auga
    0.06
    odel
    0.06
    Activations Density 0.000%

    No Known Activations