© 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. 75448
    Prev
    Next
    INDEX
    Explanations

    terms related to data removal and security policies

    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
    getc
    -0.07
    ritel
    -0.07
    ghi
    -0.07
    ãĥĥãĥĦ
    -0.07
    ãĥ
    -0.06
    à¹ģ
    -0.06
     Dirk
    -0.06
    swing
    -0.06
    ë§ī
    -0.06
    916
    -0.06
    POSITIVE LOGITS
     remaining
    0.07
    tica
    0.07
     cle
    0.07
    rahim
    0.06
     marked
    0.06
    ucz
    0.06
     destruct
    0.06
    ervas
    0.06
    ocate
    0.06
    oner
    0.06
    Activations Density 0.002%

    No Known Activations