© 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. 5-LLAMASCOPE-RES-131K
    6. 126513
    Prev
    Next
    INDEX
    Explanations

    varying percentages or proportions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    Parcelable
    -0.06
    erty
    -0.06
    entiful
    -0.06
    ebo
    -0.06
     yö
    -0.06
    pires
    -0.06
    ök
    -0.06
    rieb
    -0.06
     physical
    -0.06
    å°Ħ
    -0.06
    POSITIVE LOGITS
     Roose
    0.06
    riteln
    0.06
    ombine
    0.06
    abd
    0.06
    unma
    0.06
    .Rendering
    0.06
    ksi
    0.06
    empo
    0.06
     chaud
    0.05
     Nas
    0.05
    Activations Density 0.006%

    No Known Activations