© 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. 29-LLAMASCOPE-RES-32K
    11. 17709
    Prev
    Next
    INDEX
    Explanations

    instances of URLs and mentions of specific characters or their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fucking
    -0.22
     fucking
    -0.21
     fucked
    -0.19
    fuck
    -0.19
     shit
    -0.18
     fuck
    -0.18
     fucks
    -0.16
     bullshit
    -0.16
    _MACRO
    -0.16
     FUCK
    -0.15
    POSITIVE LOGITS
     Dil
    0.44
     dil
    0.35
     Dog
    0.26
    Dog
    0.24
     dilation
    0.23
     Rat
    0.21
     diluted
    0.21
     dog
    0.20
    dog
    0.19
     Boss
    0.18
    Activations Density 0.004%

    No Known Activations