INDEX

Explanations

actions involving physically applying or attaching items to surfaces or body parts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

estate

-0.17

ãĥ¼ãĥĢ

-0.17

zl

-0.15

 Replay

-0.15

ÐµÐ¹

-0.14

ling

-0.14

lings

-0.14

eload

-0.14

.centerY

-0.14

elize

-0.14

POSITIVE LOGITS

à¤¿à¤¯à¤°

0.15

vier

0.15

ietf

0.15

->[

0.14

alog

0.14

 ninh

0.14

 your

0.13

ienen

0.13

heimer

0.13

CJK

0.13

Activations Density 0.225%

actions involving physically applying or attaching items to surfaces or body parts

No Comments

No Known Activations