INDEX

Explanations

words or prefixes related to negation or lack

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

-0.24

ood

-0.23

ooter

-0.23

lut

-0.22

overnment

-0.22

ocket

-0.22

uard

-0.21

suming

-0.20

ensitive

-0.19

urpose

-0.19

POSITIVE LOGITS

loss

0.17

ue

0.16

used

0.16

as

0.15

elt

0.15

æ¸Ī

0.15

\common

0.15

iston

0.15

enis

0.15

right

0.15

Activations Density 0.006%

words or prefixes related to negation or lack

No Comments

No Known Activations