INDEX

Explanations

various forms of the prefix "dis" or words related to negative or undesirable outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

hind

-0.18

iley

-0.17

ong

-0.15

kad

-0.15

scriber

-0.15

jet

-0.15

kap

-0.14

het

-0.14

uples

-0.14

azon

-0.14

POSITIVE LOGITS

ellaneous

0.19

rael

0.19

naire

0.17

¼

0.16

gow

0.15

emean

0.15

ment

0.14

ettes

0.14

/dis

0.14

keit

0.14

Activations Density 0.083%

various forms of the prefix "dis" or words related to negative or undesirable outcomes

No Comments

No Known Activations