© 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. 9-LLAMASCOPE-RES-131K
    11. 95176
    Prev
    Next
    INDEX
    Explanations

    terms and operations related to memory management and freeing resources 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
    olo
    -0.08
     Brennan
    -0.08
    SSIP
    -0.08
    pany
    -0.07
    preci
    -0.07
    ldata
    -0.07
    crement
    -0.07
    ogan
    -0.07
    Deferred
    -0.07
     Deferred
    -0.06
    POSITIVE LOGITS
    unu
    0.07
    .nih
    0.06
     Regular
    0.06
    ilden
    0.06
     unused
    0.06
    _unused
    0.06
     heat
    0.05
    439
    0.05
     regular
    0.05
     PERF
    0.05
    Activations Density 0.007%

    No Known Activations