© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 17-LLAMASCOPE-RES-131K
    11. 78348
    Prev
    Next
    INDEX
    Explanations

    instances of manipulation or distortion of information

    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
    imit
    -0.08
    ãĥ³ãĤ¹
    -0.07
    ikk
    -0.06
    eker
    -0.06
     Matth
    -0.06
    umer
    -0.06
    .BO
    -0.06
    dma
    -0.06
     ØŃÚ©Ùħ
    -0.06
    OPTIONS
    -0.05
    POSITIVE LOGITS
    ört
    0.07
    gebn
    0.07
    /dist
    0.07
    benh
    0.06
    itis
    0.06
    AIT
    0.06
     inorder
    0.06
    .Stretch
    0.06
     Geschichte
    0.06
     inconvenient
    0.06
    Activations Density 0.027%

    No Known Activations