© 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. 103426
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty or bias in opinions

    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
    èĮ
    -0.08
    ìĹŃ
    -0.06
    txn
    -0.06
    engan
    -0.06
    Subscriber
    -0.06
     Weld
    -0.06
    Ñģли
    -0.06
    izza
    -0.06
    ritt
    -0.06
    άνÏī
    -0.06
    POSITIVE LOGITS
     biased
    0.11
     bias
    0.10
     biases
    0.08
     Bias
    0.08
    biased
    0.08
    bias
    0.08
    ince
    0.07
     self
    0.07
     Naturally
    0.07
    ffi
    0.07
    Activations Density 0.040%

    No Known Activations