INDEX

Explanations

phrases indicating self-evidence or obviousness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

indr

-0.16

typeorm

-0.15

celik

-0.15

¾ç¤º

-0.14

erland

-0.14

 Undefined

-0.14

 thuyáº¿t

-0.14

à¸ł

-0.14

_TypeDef

-0.14

lett

-0.13

POSITIVE LOGITS

 obvious

0.76

 Ð¾ÑĩÐµÐ²Ð¸Ð´

0.39

 obviously

0.36

 evident

0.34

 Obviously

0.31

Obviously

0.31

Ob

0.31

Âłob

0.30

-ob

0.30

 straightforward

0.30

Activations Density 0.307%

phrases indicating self-evidence or obviousness

No Comments

No Known Activations