© 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. 15-LLAMASCOPE-RES-131K
    6. 104238
    Prev
    Next
    INDEX
    Explanations

    terms related to allegations of misconduct and unethical behavior

    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
    +offset
    -0.08
    okable
    -0.07
    abcdefghijklmnop
    -0.07
    ezi
    -0.07
    duk
    -0.07
    é¼
    -0.07
    าะ
    -0.07
    zcze
    -0.07
    ови
    -0.07
    êu
    -0.07
    POSITIVE LOGITS
    bul
    0.06
    ences
    0.06
     communication
    0.06
    ler
    0.06
    d
    0.06
    cl
    0.06
    isle
    0.06
    ires
    0.06
     ana
    0.06
    t
    0.06
    Activations Density 0.016%

    No Known Activations