© 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. 28521
    Prev
    Next
    INDEX
    Explanations

    references to characters or groups with a collective ownership or identity

    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
    lev
    -0.06
    ucci
    -0.06
    anta
    -0.06
     desc
    -0.06
    اÙĥ
    -0.06
     others
    -0.05
     Chim
    -0.05
    ìĻ¸
    -0.05
     ?>"/>↵
    -0.05
     guarded
    -0.05
    POSITIVE LOGITS
     hero
    0.09
    icina
    0.08
    .sax
    0.08
    hero
    0.08
     heroine
    0.08
     heroes
    0.08
     protagonist
    0.07
    inh
    0.07
    prot
    0.07
    -hero
    0.07
    Activations Density 0.029%

    No Known Activations