© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 103308
    Prev
    Next
    INDEX
    Explanations

    phrases related to user consent and website usage policies

    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
    illes
    -0.07
    èŃ·
    -0.06
     Witness
    -0.06
    ÑĴ
    -0.06
    bé
    -0.06
    .Enums
    -0.06
    èĩªçĶ±
    -0.06
     Bud
    -0.06
    менÑĪ
    -0.06
    веÑĤ
    -0.06
    POSITIVE LOGITS
    udic
    0.07
    exo
    0.06
    etto
    0.06
    italic
    0.06
    abus
    0.06
    esse
    0.06
     Becker
    0.06
     Bew
    0.06
     kneeling
    0.06
    AGO
    0.06
    Activations Density 0.001%

    No Known Activations