INDEX

Explanations

mentions of "Hell" and related contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ibus

-0.16

noon

-0.15

okie

-0.15

Roz

-0.14

ellig

-0.14

etime

-0.14

ovich

-0.14

eway

-0.14

iliz

-0.14

Ĭ

-0.14

POSITIVE LOGITS

fire

0.22

acious

0.21

zap

0.20

inois

0.19

iday

0.18

BOUND

0.18

raising

0.17

ipt

0.17

bound

0.17

 hath

0.17

Activations Density 0.011%

mentions of "Hell" and related contexts

No Comments

No Known Activations