INDEX

Explanations

symbols or special characters frequently used in programming or markup languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 Iowa

-0.14

jax

-0.14

Ð»Ñİ

-0.14

GLOSS

-0.14

 Springs

-0.14

Ħ

-0.13

iasi

-0.13

ØŃÙĦ

-0.13

ecret

-0.13

_java

-0.12

POSITIVE LOGITS

 mixin

0.23

{.

0.22

nim

0.22

writeln

0.21

 pragma

0.21

 writeln

0.21

riteln

0.21

Nim

0.20

nim

0.20

proc

0.19

Activations Density 0.005%

symbols or special characters frequently used in programming or markup languages

No Comments

No Known Activations