INDEX

Explanations

references to faith

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

iment

-0.18

arium

-0.16

Ļ

-0.16

er

-0.15

ÙĨØ¨

-0.14

å¹ķ

-0.14

åĳĺ

-0.14

è¾

-0.14

_feedback

-0.14

.fastjson

-0.14

POSITIVE LOGITS

fulness

0.28

fully

0.25

lessly

0.23

ful

0.19

FUL

0.19

full

0.18

quake

0.18

worthy

0.17

less

0.16

Activations Density 0.021%

references to faith

No Comments

No Known Activations