INDEX

Explanations

citations and references within academic writing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ermen

-0.15

vej

-0.15

Bru

-0.14

//{{

-0.14

OLON

-0.14

.identity

-0.13

Bru

-0.13

iator

-0.13

erman

-0.13

odega

-0.13

POSITIVE LOGITS

ka

0.16

ellig

0.16

 fmap

0.15

zl

0.14

.vs

0.14

_NT

0.14

/umd

0.14

/|

0.13

idal

0.13

 Grove

0.13

Activations Density 0.049%

citations and references within academic writing

No Comments

No Known Activations