INDEX

Explanations

instances of the word "en" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

aca

-0.17

eden

-0.16

gro

-0.16

.getPage

-0.15

caff

-0.15

æľ

-0.14

ÅĽcie

-0.14

UZ

-0.14

 getCount

-0.14

Haz

-0.14

POSITIVE LOGITS

.Assertions

0.14

.Safe

0.14

 å¥

0.14

_NETWORK

0.14

\Container

0.13

 Infos

0.13

Ø§ÙĤ

0.13

ÑĢÐ´

0.13

rd

0.13

Activations Density 0.001%

instances of the word "en" in various contexts

No Comments

No Known Activations