© 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. 129204
    Prev
    Next
    INDEX
    Explanations

    technical terms related to signal processing and calibration methods

    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
    aban
    -0.06
    andles
    -0.06
    ua
    -0.06
    andler
    -0.06
    enco
    -0.06
    mach
    -0.06
    atron
    -0.06
     Interr
    -0.06
     Games
    -0.05
    -sensitive
    -0.05
    POSITIVE LOGITS
     tapped
    0.07
     Signal
    0.07
    fell
    0.07
     dsp
    0.07
     Trev
    0.07
     dép
    0.07
     Welch
    0.07
     intptr
    0.07
     Hardware
    0.07
    еÑĢаÑĤÑĥ
    0.07
    Activations Density 0.458%

    No Known Activations