© 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. 22-LLAMASCOPE-RES-131K
    6. 3976
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ville
    -0.08
    ahun
    -0.07
    inde
    -0.07
    allo
    -0.07
    dbuf
    -0.06
    ÑĢаг
    -0.06
     hele
    -0.06
    ahoma
    -0.06
    /cgi
    -0.06
    alc
    -0.06
    POSITIVE LOGITS
    abler
    0.07
    ToPoint
    0.06
     nutshell
    0.06
     respectively
    0.06
     киÑģ
    0.06
    dropIfExists
    0.06
    cling
    0.06
    æ¶ī
    0.05
    -spin
    0.05
     practical
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.