© 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. 29590
    Prev
    Next
    INDEX
    Explanations

    programming and technical syntax elements

    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
    otte
    -0.07
    alse
    -0.07
    itzer
    -0.07
    ulla
    -0.07
    olla
    -0.06
    asso
    -0.06
    omon
    -0.06
    avic
    -0.06
    anced
    -0.06
    tern
    -0.06
    POSITIVE LOGITS
    importe
    0.07
    orelease
    0.06
     lay
    0.06
     FE
    0.06
     mest
    0.06
    ãĤ¦ãĤ§
    0.06
    ãĥĭãĥ¼
    0.06
    ][/
    0.06
    DisplayStyle
    0.06
     remotely
    0.06
    Activations Density 0.000%

    No Known Activations