INDEX

Explanations

quantitative data, particularly numbers associated with measurements or evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

(*.

-0.17

illac

-0.15

/styles

-0.15

åŀĤ

-0.15

 etiqu

-0.15

Ghost

-0.15

nop

-0.14

atcher

-0.14

 bÃ¥de

-0.14

icens

-0.14

POSITIVE LOGITS

kle

0.18

 Peters

0.14

vae

0.14

QRST

0.14

EN

0.14

le

0.14

anda

0.14

dit

0.14

sk

0.14

_cred

0.14

Activations Density 0.047%

quantitative data, particularly numbers associated with measurements or evaluations

No Comments

No Known Activations