INDEX

Explanations

instances of the verb "be" in various forms and contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

Glo

-0.16

 Gould

-0.15

ictory

-0.15

 McKenzie

-0.15

 amen

-0.14

phere

-0.14

 Kann

-0.14

urgeon

-0.14

naire

-0.14

POSITIVE LOGITS

ardless

0.19

ardon

0.17

elman

0.15

beeld

0.15

ech

0.14

evin

0.14

rong

0.14

 sure

0.14

edo

0.14

upt

0.14

Activations Density 0.031%

instances of the verb "be" in various forms and contexts

No Comments

No Known Activations