© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 78208
    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
     Consortium
    -0.07
    onga
    -0.07
    ´Ŀ
    -0.06
    PLEX
    -0.06
    EntityManager
    -0.06
    askell
    -0.06
    EW
    -0.06
    ãĥ³ãĥĩãĤ£
    -0.06
    /Common
    -0.06
     {*
    -0.06
    POSITIVE LOGITS
    an
    0.07
    διά
    0.07
     Glover
    0.06
     Vend
    0.06
    umps
    0.06
    ason
    0.06
    asa
    0.06
    åı·
    0.06
    먹
    0.06
    asons
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.