INDEX

Explanations

modal verbs indicating ability or possibility

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

èĥ½å¤Ł

-0.20

èĥ½

-0.19

 BÃĸL

-0.15

eree

-0.15

»¿

-0.15

icens

-0.14

 kunnen

-0.14

 correctly

-0.13

asons

-0.13

acco

-0.13

POSITIVE LOGITS

’t

0.28

't

0.27

berra

0.23

opies

0.22

be

0.21

/w

0.21

isters

0.20

alic

0.20

ister

0.19

VAS

0.19

Activations Density 0.236%

modal verbs indicating ability or possibility

No Comments

No Known Activations