© 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. 9-LLAMASCOPE-RES-131K
    11. 95707
    Prev
    Next
    INDEX
    Explanations

    elements related to software and security management

    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
    alone
    -0.07
    ulumi
    -0.06
     Kemp
    -0.06
     Sob
    -0.06
    &R
    -0.06
     ie
    -0.06
     ISSN
    -0.06
    acro
    -0.06
    ied
    -0.06
    mall
    -0.06
    POSITIVE LOGITS
    enan
    0.08
    ulp
    0.07
     Vall
    0.07
    icho
    0.07
    rosis
    0.07
    vel
    0.06
    uali
    0.06
    osit
    0.06
    udad
    0.06
    erals
    0.06
    Activations Density 0.003%

    No Known Activations