© 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. 104233
    Prev
    Next
    INDEX
    Explanations

    initialization functions and methods in code

    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
     Gros
    -0.08
    nicas
    -0.08
    lint
    -0.07
    pii
    -0.07
    unca
    -0.07
    .metro
    -0.07
    bao
    -0.06
     ch
    -0.06
    idan
    -0.06
    oder
    -0.06
    POSITIVE LOGITS
    efault
    0.07
     solids
    0.07
    __(↵
    0.06
    ago
    0.06
    xFFFFFFFF
    0.06
    agger
    0.06
    \OptionsResolver
    0.06
    ãĥĭãĥ¼
    0.06
    __(
    0.06
    çĪ½
    0.06
    Activations Density 0.000%

    No Known Activations