© 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. 5-LLAMASCOPE-RES-131K
    11. 125845
    Prev
    Next
    INDEX
    Explanations

    references to personal relationships

    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
    crap
    -0.06
    leine
    -0.06
    izin
    -0.06
    OMIC
    -0.06
    los
    -0.06
     ant
    -0.05
    ucker
    -0.05
    ÏĢε
    -0.05
     interpre
    -0.05
    ég
    -0.05
    POSITIVE LOGITS
    بس
    0.08
    ç¬
    0.07
    _LOOKUP
    0.07
    aiser
    0.07
    ENCH
    0.07
     maduras
    0.07
     Sunder
    0.07
     lesbi
    0.07
    amedi
    0.06
    üstü
    0.06
    Activations Density 0.003%

    No Known Activations