© 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. 106356
    Prev
    Next
    INDEX
    Explanations

    concepts related to translation and language adaptation challenges

    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
    addir
    -0.07
     hod
    -0.07
    decor
    -0.07
    Äĥr
    -0.06
    .mods
    -0.06
    illos
    -0.06
    ckill
    -0.06
    peri
    -0.06
    ardown
    -0.06
    ucher
    -0.06
    POSITIVE LOGITS
     ç¿
    0.07
    ç¿»
    0.07
    arb
    0.07
    babel
    0.07
     profession
    0.07
     INLINE
    0.06
     ë²Ī
    0.06
    -trans
    0.06
    aket
    0.06
    _mt
    0.06
    Activations Density 0.011%

    No Known Activations