© 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. 57528
    Prev
    Next
    INDEX
    Explanations

    terms related to audio calibration and measurement variations

    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
    .Designer
    -0.06
    ha
    -0.06
    ecies
    -0.06
     ec
    -0.06
    perms
    -0.06
    vir
    -0.06
    wan
    -0.06
    clc
    -0.06
    анг
    -0.06
    æĥħ
    -0.05
    POSITIVE LOGITS
    ikh
    0.08
    ffen
    0.08
    nea
    0.07
    isay
    0.07
    IFO
    0.07
    essler
    0.07
     drift
    0.07
     systematic
    0.07
     vign
    0.07
    ildo
    0.07
    Activations Density 0.044%

    No Known Activations