INDEX

Explanations

parentheses and their associated content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

iki

-0.17

arde

-0.15

REDIS

-0.14

 presente

-0.14

.Dom

-0.14

@Resource

-0.14

é«ĺæ¸ħ

-0.14

Ã¶st

-0.14

Ì£

-0.14

Ð³Ð¾ÑĤ

-0.14

POSITIVE LOGITS

abbrev

0.21

 abbreviated

0.17

0.14

oles

0.14

akens

0.14

abbr

0.14

oso

0.14

aka

0.14

Ø±ÙĪÙĩ

0.13

Activations Density 0.064%

parentheses and their associated content

No Comments

No Known Activations