INDEX

Explanations

nouns and phrases related to tangible entities or physical objects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

vÃ©

-0.17

 Morrow

-0.17

èħ

-0.16

ayan

-0.16

_xor

-0.16

dera

-0.16

Ã¢u

-0.16

-0.15

Å¼e

-0.15

seealso

-0.15

POSITIVE LOGITS

-with

0.36

ith

0.31

-With

0.28

—with

0.26

Mit

0.25

Wit

0.24

WITH

0.24

.With

0.23

WI

0.23

ITH

0.23

Activations Density 0.223%

nouns and phrases related to tangible entities or physical objects

No Comments

No Known Activations