© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 126410
    Prev
    Next
    INDEX
    Explanations

    phrases related to individual achievements and contributions

    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
    oha
    -0.07
    éĹ²
    -0.06
    ucker
    -0.06
    æł¹æľ¬
    -0.06
    acket
    -0.06
    SED
    -0.06
    è®
    -0.06
    OTS
    -0.06
    CONDS
    -0.06
    aren
    -0.06
    POSITIVE LOGITS
     accomplish
    0.08
     contribution
    0.07
     accomplishments
    0.07
     done
    0.07
     accomplished
    0.07
     contributions
    0.07
    adir
    0.06
     Guard
    0.06
    _tac
    0.06
     GIS
    0.06
    Activations Density 0.020%

    No Known Activations