INDEX

Explanations

forms of the verb "to 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 @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

lust

-0.19

zag

-0.16

atism

-0.16

anel

-0.16

ecies

-0.15

pants

-0.15

icz

-0.15

atica

-0.14

POSITIVE LOGITS

plitude

0.27

ERICAN

0.23

putation

0.22

plit

0.22

iable

0.21

munition

0.21

oxic

0.20

eba

0.19

oba

0.19

igos

0.19

Activations Density 0.029%

forms of the verb "to be" in various contexts

No Comments

No Known Activations