INDEX

Explanations

instances of the word "or" 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 @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

elli

-0.16

-0.15

ä¸Ķ

-0.15

enticate

-0.15

eenth

-0.15

enstein

-0.15

-0.14

redient

-0.14

asmine

-0.14

POSITIVE LOGITS

few

0.19

 longer

0.19

 more

0.18

few

0.18

so

0.18

cas

0.18

 less

0.17

 sooner

0.16

iddi

0.15

two

0.15

Activations Density 0.021%

instances of the word "or" in various contexts

No Comments

No Known Activations