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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 29827
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     totally
    -0.06
    atan
    -0.06
     rather
    -0.06
    enn
    -0.06
     accept
    -0.06
     pent
    -0.05
     plus
    -0.05
     sports
    -0.05
     may
    -0.05
    ich
    -0.05
    POSITIVE LOGITS
     fucks
    0.07
    RIX
    0.07
    è¸
    0.07
     âĸĪ
    0.07
    اض
    0.07
     fucked
    0.07
    áºŃp
    0.07
    ENCY
    0.07
     handjob
    0.07
    evity
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.