INDEX

Explanations

variations of the word "ravish" or any related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

opher

-0.15

ownership

-0.15

SizeMode

-0.15

èĿ

-0.14

 underlying

-0.14

antity

-0.14

hq

-0.14

apur

-0.14

ribbon

-0.13

å¤ĩ

-0.13

POSITIVE LOGITS

eting

0.20

aged

0.19

aget

0.18

ages

0.18

AGED

0.17

alling

0.16

erview

0.16

ager

0.16

upy

0.15

aging

0.15

Activations Density 0.004%

variations of the word "ravish" or any related terms

No Comments

No Known Activations