© 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. 15-LLAMASCOPE-RES-131K
    11. 89078
    Prev
    Next
    INDEX
    Explanations

    phrases indicating lack or absence of something essential

    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
    RESS
    -0.07
    anten
    -0.07
    yang
    -0.07
    ant
    -0.06
     wherever
    -0.06
    otts
    -0.06
    eil
    -0.06
    alm
    -0.06
    ola
    -0.06
     whenever
    -0.06
    POSITIVE LOGITS
    tul
    0.09
     proper
    0.07
    иÑģлов
    0.07
    inue
    0.07
    acher
    0.07
    ramer
    0.07
     accom
    0.06
    proper
    0.06
     Proper
    0.06
    иÑĤеÑĤ
    0.06
    Activations Density 0.008%

    No Known Activations