© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 29518
    Prev
    Next
    INDEX
    Explanations

    possessive forms of nouns

    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
    aal
    -0.07
    NavController
    -0.07
    etur
    -0.07
     Dün
    -0.07
    odd
    -0.07
    è¼Ŀ
    -0.07
     Kidd
    -0.06
    yms
    -0.06
    ÑĤÑı
    -0.06
     zev
    -0.06
    POSITIVE LOGITS
     been
    0.11
     gonna
    0.11
     not
    0.10
     gone
    0.08
    been
    0.08
     done
    0.08
     afraid
    0.08
    'e
    0.07
     got
    0.07
     Been
    0.07
    Activations Density 0.050%

    No Known Activations