INDEX

Explanations

instances of the word "go" 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 @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

mente

-0.24

ly

-0.19

ÏģÎ¹Î¿

-0.16

meer

-0.16

raz

-0.16

udd

-0.15

ro

-0.15

ëŁ¬

-0.15

uet

-0.15

raph

-0.15

POSITIVE LOGITS

ÅĤÄħ

0.20

her

0.18

à¸£à¸©

0.18

erner

0.17

adget

0.16

-away

0.16

ob

0.15

thic

0.15

away

0.15

vw

0.15

Activations Density 0.083%

instances of the word "go" in various contexts

No Comments

No Known Activations