© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 82222
    Prev
    Next
    INDEX
    Explanations

    phrases related to suspicion or discussing mysterious situations

    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
    imar
    -0.07
    anel
    -0.07
    Ðĩ
    -0.07
    webtoken
    -0.07
    zel
    -0.07
     обÑĢазом
    -0.07
    å±±å¸Ĥ
    -0.07
    indow
    -0.06
    ån
    -0.06
    ãĤīãģĦ
    -0.06
    POSITIVE LOGITS
     get
    0.07
     Jungle
    0.06
     apt
    0.06
     run
    0.06
     gets
    0.06
     Jap
    0.06
     backbone
    0.05
     nab
    0.05
     boosting
    0.05
     Medieval
    0.05
    Activations Density 0.007%

    No Known Activations