© 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. 61889
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface styling and layout components in programming

    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
     rep
    -0.06
     prospective
    -0.06
     Ga
    -0.06
    osh
    -0.06
     w
    -0.05
    ãģ¾ãģŁ
    -0.05
     Cle
    -0.05
    uar
    -0.05
    è¯Ŀ
    -0.05
     cracks
    -0.05
    POSITIVE LOGITS
    essim
    0.08
    ahren
    0.08
    utenberg
    0.07
    ssel
    0.07
    rena
    0.07
    jem
    0.07
    ÚĺÛĮ
    0.07
    emin
    0.07
    ëĭĪëĭ¤
    0.07
    ully
    0.07
    Activations Density 0.000%

    No Known Activations