© 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. 459
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal values and integrity

    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
    kov
    -0.07
    çĶ²
    -0.06
    opa
    -0.06
    صÙĨ
    -0.06
    jerne
    -0.06
     DisplayName
    -0.06
     Replies
    -0.06
    onis
    -0.06
    opal
    -0.06
    ChangedEventArgs
    -0.06
    POSITIVE LOGITS
    alse
    0.07
    inux
    0.06
    lbrace
    0.06
    cts
    0.06
    ulus
    0.06
     unless
    0.06
    301
    0.06
    atron
    0.06
    åıªæľī
    0.06
    succ
    0.06
    Activations Density 0.073%

    No Known Activations