© 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. 116836
    Prev
    Next
    INDEX
    Explanations

    compound words or phrases that suggest overcoming obstacles or breaking boundaries

    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
    ções
    -0.07
    ahlen
    -0.07
    wan
    -0.06
    vore
    -0.06
    uras
    -0.06
    jab
    -0.06
     Priv
    -0.06
    oram
    -0.06
    ised
    -0.06
    enha
    -0.06
    POSITIVE LOGITS
    edException
    0.08
    ableView
    0.07
     Kostenlos
    0.07
    .vm
    0.07
    ISCO
    0.06
    TING
    0.06
    ingly
    0.06
    ãģ®ãģĬ
    0.06
    625
    0.06
    780
    0.06
    Activations Density 0.044%

    No Known Activations