© 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. 84411
    Prev
    Next
    INDEX
    Explanations

    references to specific documents or reports related to cost and analysis

    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
    bel
    -0.07
    Fax
    -0.06
     affair
    -0.06
     something
    -0.06
    andy
    -0.06
     stuff
    -0.06
    mas
    -0.06
    ANTA
    -0.06
    v
    -0.05
    ick
    -0.05
    POSITIVE LOGITS
    raison
    0.08
    odash
    0.08
     baiser
    0.08
    pdata
    0.08
    ÑĤÑİ
    0.08
    egov
    0.07
    ogui
    0.07
    utut
    0.07
    ÄĻd
    0.07
    ä¸ĺ
    0.07
    Activations Density 0.049%

    No Known Activations