INDEX

Explanations

references to unknown or ambiguous situations or events

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

fait

-0.17

mps

-0.16

("'"

-0.14

ramer

-0.14

onde

-0.14

ghan

-0.14

oyal

-0.14

ÑģÐ¾ÑĤ

-0.13

 Hills

-0.13

POSITIVE LOGITS

 wrong

0.27

wrong

0.25

 Wrong

0.23

Wrong

0.23

 WRONG

0.19

 fish

0.18

_wrong

0.16

 missing

0.16

bjerg

0.16

 Missing

0.16

Activations Density 0.044%

references to unknown or ambiguous situations or events

No Comments

No Known Activations