INDEX

Explanations

phrases describing a range of values or quantities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

roz

-0.18

emiz

-0.16

arity

-0.15

ufe

-0.15

achuset

-0.15

uration

-0.15

onian

-0.15

unker

-0.15

eniable

-0.15

ichern

-0.14

POSITIVE LOGITS

esser

0.17

ÎºÎ·

0.14

ces

0.14

GetSize

0.14

Dol

0.14

 Butter

0.14

Ã¶rt

0.13

dw

0.13

TypeEnum

0.13

LOSE

0.13

Activations Density 0.016%

phrases describing a range of values or quantities

No Comments

No Known Activations