© 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. 15-LLAMASCOPE-RES-131K
    11. 103983
    Prev
    Next
    INDEX
    Explanations

    phrases indicating existence or reference to specific issues

    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
    rah
    -0.08
    roach
    -0.07
    /string
    -0.06
    iddles
    -0.06
    ament
    -0.06
    rž
    -0.06
    á»Ĩ
    -0.06
    316
    -0.06
    own
    -0.06
    Exactly
    -0.06
    POSITIVE LOGITS
    ë©
    0.07
    .cleanup
    0.07
    âĸį
    0.07
     aspect
    0.06
    Wunused
    0.06
    æĶ
    0.06
    esser
    0.06
    ebek
    0.06
    icari
    0.06
    icular
    0.06
    Activations Density 0.029%

    No Known Activations