© 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. 55929
    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
    opup
    -0.08
    uml
    -0.08
    oproject
    -0.07
    οκ
    -0.07
    rax
    -0.07
    OOM
    -0.07
    ư
    -0.07
    "class
    -0.07
    https
    -0.07
    inki
    -0.07
    POSITIVE LOGITS
    áo
    0.07
     reinst
    0.06
     overdose
    0.06
    (s
    0.06
    discard
    0.06
    ijkstra
    0.06
    contri
    0.06
     Katz
    0.05
    pending
    0.05
    gan
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.