© 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. 17-LLAMASCOPE-RES-131K
    11. 125111
    Prev
    Next
    INDEX
    Explanations

    programming code snippets and commands related to settings and configurations

    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
    afen
    -0.07
    ghan
    -0.06
    heim
    -0.06
    ambre
    -0.06
    hra
    -0.06
    aws
    -0.06
    unda
    -0.06
     å£
    -0.06
    912
    -0.06
    erset
    -0.06
    POSITIVE LOGITS
    uitka
    0.08
    ì§ľ
    0.07
    анÑĸÑĤ
    0.07
    elin
    0.07
    ãĢĬ
    0.07
     ãĢĪ
    0.06
    OwnProperty
    0.06
    ãĢĪ
    0.06
     titled
    0.06
    ahoo
    0.06
    Activations Density 0.052%

    No Known Activations