© 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. 27006
    Prev
    Next
    INDEX
    Explanations

    references to causation or conditions related to actions or events

    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
    ais
    -0.07
    uis
    -0.06
    agar
    -0.06
    ait
    -0.05
     Gap
    -0.05
    eki
    -0.05
    erton
    -0.05
    ide
    -0.05
    -
    -0.05
     or
    -0.05
    POSITIVE LOGITS
    åµ
    0.08
     ÄĮer
    0.08
    oord
    0.07
    #ab
    0.07
    SGlobal
    0.07
    _defaults
    0.07
    illes
    0.07
    .opend
    0.07
    tle
    0.07
    onto
    0.07
    Activations Density 0.043%

    No Known Activations