© 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. 78782
    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
     Trusted
    -0.06
    -gnu
    -0.06
    elli
    -0.06
    æ´
    -0.06
    hk
    -0.06
    enden
    -0.06
    ceans
    -0.06
     Mercer
    -0.06
    SEG
    -0.06
    otu
    -0.06
    POSITIVE LOGITS
    PMC
    0.07
    rost
    0.07
    ORB
    0.07
    èĥİ
    0.07
    esel
    0.07
     åı¸
    0.06
    adge
    0.06
    ÃŃc
    0.06
    JOR
    0.06
     ï¼ļ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.