INDEX

Explanations

statements related to legal arguments and assertions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

zet

-0.14

rik

-0.14

ulti

-0.14

#undef

-0.14

ÑĢÐ¸Ðº

-0.13

adas

-0.13

 inventory

-0.13

eless

-0.13

kar

-0.13

ult

-0.13

POSITIVE LOGITS

 ráº±ng

0.36

 that

0.34

 bahwa

0.34

that

0.28

	that

0.26

 ÏĮÏĦÎ¹

0.25

 dass

0.23

 ettÃ¤

0.22

 ÑĩÑĤÐ¾

0.22

 Å¼e

0.21

Activations Density 0.311%

statements related to legal arguments and assertions

No Comments

No Known Activations

statements related to legal arguments and assertions

No Comments

No Known Activations