INDEX

Explanations

mentions of reasons or explanations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

asco

-0.18

 whats

-0.14

iam

-0.14

ÑģÐ¾ÑĢ

-0.13

GAN

-0.13

&&(

-0.13

ãģ¦ãĤĤ

-0.13

das

-0.13

ily

-0.13

xec

-0.13

POSITIVE LOGITS

 that

0.26

that

0.23

 they

0.19

we

0.18

 ÏĢÎ¿Ïħ

0.17

 ÑĩÑĤÐ¾

0.17

 mÃł

0.16

 dass

0.16

 bahwa

0.16

 ráº±ng

0.16

Activations Density 0.079%

mentions of reasons or explanations

No Comments

No Known Activations