© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 62375
    Prev
    Next
    INDEX
    Explanations

    phrases related to diagnostic methods and their effectiveness

    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
    ijľ
    -0.07
    æħĭ
    -0.07
     komp
    -0.06
    867
    -0.06
     Preservation
    -0.06
     schl
    -0.06
    नल
    -0.06
     Odin
    -0.06
     Ulus
    -0.06
     иÑģÑħод
    -0.06
    POSITIVE LOGITS
     only
    0.12
     limited
    0.12
     limitations
    0.11
    åıªèĥ½
    0.11
     limits
    0.10
     limitation
    0.10
    only
    0.10
    limited
    0.10
     Limit
    0.09
    limitations
    0.09
    Activations Density 0.081%

    No Known Activations