© 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. 9-LLAMASCOPE-RES-131K
    11. 95829
    Prev
    Next
    INDEX
    Explanations

    email headers and metadata

    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
    lica
    -0.06
    mons
    -0.05
     sheets
    -0.05
    asons
    -0.05
    оÑĩ
    -0.05
    eneric
    -0.05
    worthy
    -0.05
    ason
    -0.05
    arden
    -0.05
     cod
    -0.05
    POSITIVE LOGITS
    557
    0.08
     Hlav
    0.07
    OVE
    0.07
    .chunk
    0.07
     Erotik
    0.07
    Äįan
    0.07
    åł´
    0.07
    ONTAL
    0.06
    491
    0.06
    enville
    0.06
    Activations Density 0.007%

    No Known Activations