© 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. 5-LLAMASCOPE-RES-131K
    11. 126416
    Prev
    Next
    INDEX
    Explanations

    technical terms and code-related components

    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
    fak
    -0.07
    ообÑĢаз
    -0.06
    ounder
    -0.06
    lse
    -0.06
    Å¡ku
    -0.06
    biz
    -0.06
    ÙĬÙĤ
    -0.06
    éº
    -0.06
    ษ
    -0.06
    ponent
    -0.06
    POSITIVE LOGITS
    adt
    0.07
    å»Ĭ
    0.07
    caff
    0.07
    cht
    0.06
    leme
    0.06
    rox
    0.06
    ors
    0.06
    Timeout
    0.06
    ory
    0.06
     ogs
    0.06
    Activations Density 0.000%

    No Known Activations