Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 61079
    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
    OUCH
    -0.07
    меÑĩ
    -0.07
     má»±c
    -0.06
    ekil
    -0.06
    دا
    -0.06
    adena
    -0.06
     Mey
    -0.06
     part
    -0.06
    Setup
    -0.06
    uzey
    -0.06
    POSITIVE LOGITS
     blah
    0.08
    PushButton
    0.06
    å¶
    0.06
    onga
    0.06
    fetchAll
    0.06
    angler
    0.06
    -margin
    0.06
    .metamodel
    0.06
    opp
    0.06
     kuru
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.