© 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. 61461
    Prev
    Next
    INDEX
    Explanations

    terms related to definitions and classifications in various contexts

    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
    omm
    -0.07
    lá
    -0.06
     Mandatory
    -0.06
     slu
    -0.06
    216
    -0.06
    vip
    -0.06
     ali
    -0.05
    JsonValue
    -0.05
    omy
    -0.05
     dostan
    -0.05
    POSITIVE LOGITS
     definition
    0.08
    definition
    0.08
     Definition
    0.08
    -definition
    0.07
     versus
    0.07
    iners
    0.07
    Definition
    0.07
     вообÑīе
    0.07
    vs
    0.07
     vs
    0.07
    Activations Density 0.046%

    No Known Activations