INDEX

Explanations

console log statements in code snippets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

zos

-0.15

agna

-0.15

"",↵

-0.14

 vÃŃde

-0.14

atrice

-0.14

apter

-0.14

chia

-0.14

Ú¯Ø§Ø¨

-0.13

ardu

-0.13

etler

-0.13

POSITIVE LOGITS

0.21

_inside

0.18

0.17

 called

0.17

 Called

0.16

ï¼»

0.16

Called

0.16

inside

0.15

Inside

0.15

 Inside

0.15

Activations Density 0.027%

console log statements in code snippets

No Comments

No Known Activations