© 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. 26793
    Prev
    Next
    INDEX
    Explanations

    image file formats and naming conventions

    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
    igo
    -0.07
    erval
    -0.07
     jist
    -0.06
    oustic
    -0.06
    lint
    -0.05
    rego
    -0.05
    &q
    -0.05
    esse
    -0.05
    ãĥ¼ãĥī
    -0.05
    ike
    -0.05
    POSITIVE LOGITS
    unfold
    0.07
    uild
    0.07
    ãĥĶãĥ¼
    0.07
    تÙĬÙĨ
    0.07
    ï¸
    0.07
    ledik
    0.07
    elerik
    0.07
    몰
    0.06
    Ionic
    0.06
    ENCE
    0.06
    Activations Density 0.004%

    No Known Activations