© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 15730
    Prev
    Next
    INDEX
    Explanations

    statements emphasizing finality or conclusions

    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
    елем
    -0.07
    opis
    -0.07
    onder
    -0.07
    ea
    -0.06
    ладÑĥ
    -0.06
    UNE
    -0.06
    quin
    -0.06
    ssi
    -0.06
    REFERRED
    -0.06
    onde
    -0.06
    POSITIVE LOGITS
    oland
    0.07
    976
    0.07
     sorry
    0.06
     nothing
    0.06
    weg
    0.06
     no
    0.06
    quiv
    0.06
     simple
    0.06
    isel
    0.06
    ivil
    0.06
    Activations Density 0.004%

    No Known Activations