© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 105363
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the concept of hope or resilience

    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
     nackte
    -0.08
    ucken
    -0.07
     liá»ĩu
    -0.07
    getOption
    -0.07
    ikal
    -0.07
    OPSIS
    -0.07
    ]={↵
    -0.07
    cratch
    -0.07
    NotificationCenter
    -0.07
    =\"$
    -0.07
    POSITIVE LOGITS
     someone
    0.10
     somebody
    0.10
     somewhere
    0.07
     something
    0.07
    someone
    0.07
     contr
    0.06
     Someone
    0.06
    acco
    0.06
     SOME
    0.06
     ifs
    0.06
    Activations Density 0.010%

    No Known Activations