INDEX

Explanations

the verb "be" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

pees

-0.18

adb

-0.16

ante

-0.14

pee

-0.14

hydr

-0.14

.DialogResult

-0.13

utr

-0.13

oders

-0.13

weetalert

-0.13

recision

-0.13

POSITIVE LOGITS

orgia

0.20

ibo

0.16

ãĥ³ãĥĢ

0.15

agrant

0.14

ë¡ľëĵľ

0.14

 affecting

0.14

Ð²Ð°Ð½Ð¾

0.14

<dyn

0.14

 affected

0.13

 Burgess

0.13

Activations Density 0.114%

the verb "be" in various contexts

No Comments

No Known Activations