© 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. 127730
    Prev
    Next
    INDEX
    Explanations

    instances of the word "log" and its variations, indicating a focus on login-related actions or features

    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
    oice
    -0.08
    _DL
    -0.07
    /Runtime
    -0.07
    Ľå»º
    -0.06
    渡
    -0.06
    anche
    -0.06
    ÑĥÑĩа
    -0.06
    czy
    -0.06
    ilos
    -0.06
    ÌĨ
    -0.06
    POSITIVE LOGITS
     onto
    0.08
    _into
    0.08
     into
    0.08
    into
    0.07
     vÃło
    0.07
    onto
    0.07
    .crm
    0.06
    ะ
    0.06
    /logout
    0.06
    oub
    0.06
    Activations Density 0.003%

    No Known Activations