© 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. 87799
    Prev
    Next
    INDEX
    Explanations

    events and references to significant concepts or conditions

    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
     figure
    -0.06
    708
    -0.06
    ney
    -0.06
    neys
    -0.06
    éĤ£æł·
    -0.06
     Bren
    -0.06
    val
    -0.06
    igue
    -0.06
     persistent
    -0.06
    _TLS
    -0.06
    POSITIVE LOGITS
    argas
    0.09
    ighter
    0.07
    머ëĭĪ
    0.07
    าà¸ķร
    0.07
    ivia
    0.07
    cura
    0.07
     Moment
    0.07
    ÛĮتÛĮ
    0.07
    nock
    0.06
    acket
    0.06
    Activations Density 0.066%

    No Known Activations