© 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. 84073
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and emotions

    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
    rne
    -0.06
    Ľi
    -0.06
    ils
    -0.05
     Stewart
    -0.05
    lord
    -0.05
     Burnett
    -0.05
     Chan
    -0.05
    ãĥªãĥ¼
    -0.05
    __$
    -0.05
     ne
    -0.05
    POSITIVE LOGITS
     unto
    0.11
    ä½ľä¸º
    0.08
     forKey
    0.08
    à¹Ħว
    0.08
     sebagai
    0.08
     kepada
    0.08
     onto
    0.07
    onto
    0.07
    ä¾Ľ
    0.07
     ÏīÏĤ
    0.07
    Activations Density 0.098%

    No Known Activations