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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 28-LLAMASCOPE-RES-32K
    11. 30187
    Prev
    Next
    INDEX
    Explanations

    references to social themes and concepts, particularly socialism and social media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çak
    -0.16
    haft
    -0.15
    _handling
    -0.15
    ÑĨей
    -0.15
    esome
    -0.14
    platz
    -0.14
    430
    -0.14
    ocommerce
    -0.14
    KeyListener
    -0.14
    .jasper
    -0.14
    POSITIVE LOGITS
    ite
    0.29
    ites
    0.23
     media
    0.22
     worker
    0.22
     justice
    0.21
    -media
    0.20
     Worker
    0.20
     workers
    0.20
     butterfly
    0.19
    -dist
    0.19
    Activations Density 0.021%

    No Known Activations