INDEX

Explanations

code-related terminology and constructs

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Language

-0.15

_tolerance

-0.15

è¯Ńè¨Ģ

-0.15

 tranh

-0.14

Language

-0.14

]={↵

-0.14

 language

-0.14

 Languages

-0.14

.HtmlControls

-0.13

_language

-0.13

POSITIVE LOGITS

 level

0.30

 levels

0.28

level

0.27

 LogLevel

0.26

 logger

0.25

log

0.25

 Level

0.25

 logging

0.25

 console

0.25

 LEVEL

0.24

Activations Density 0.043%

code-related terminology and constructs

No Comments

No Known Activations