INDEX

Explanations

programming-related keywords and commands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ÅĻej

-0.15

 chair

-0.14

 freeze

-0.14

zier

-0.14

iÅŁ

-0.14

ahoma

-0.13

uppet

-0.13

loquent

-0.13

hair

-0.13

ä¼Ļ

-0.13

POSITIVE LOGITS

 getopt

0.22

_OPTS

0.17

ieux

0.17

ç¶

0.17

CommandLine

0.17

 command

0.17

0.16

 help

0.16

.Help

0.15

command

0.15

Activations Density 0.039%

programming-related keywords and commands

No Comments

No Known Activations