© 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. 2-LLAMASCOPE-RES-32K
    11. 20694
    Prev
    Next
    INDEX
    Explanations

    instances of the word "banned" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ίνα
    -0.17
    ential
    -0.16
    raz
    -0.15
     Mont
    -0.15
    xbd
    -0.15
     Hint
    -0.15
    leasing
    -0.15
    имеÑĢ
    -0.14
    寸
    -0.14
    217
    -0.13
    POSITIVE LOGITS
    quets
    0.17
    rug
    0.17
    å¹ķ
    0.17
    лÑĸд
    0.16
    /lic
    0.15
    conds
    0.15
    AMED
    0.15
    strup
    0.15
    318
    0.15
     æŃ
    0.14
    Activations Density 0.028%

    No Known Activations