INDEX

Explanations

repeated patterns or markers related to code documentation or annotations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ibs

-0.17

rees

-0.15

.libs

-0.15

opoulos

-0.14

cade

-0.14

bud

-0.14

à¸°

-0.14

 tranh

-0.14

acz

-0.14

rese

-0.14

POSITIVE LOGITS

iston

0.18

#__

0.15

antro

0.15

æ·

0.14

Ð½ÑĸÐ²ÐµÑĢ

0.14

PCODE

0.14

LOT

0.14

iyel

0.14

 Juli

0.13

rÃ¥

0.13

Activations Density 0.005%

repeated patterns or markers related to code documentation or annotations

No Comments

No Known Activations