INDEX

Explanations

terms related to medical and scientific research, particularly in relation to cells, proteins, and psychological studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

icky

-0.18

ick

-0.16

uh

-0.16

nees

-0.16

 Serialized

-0.15

tt

-0.15

steen

-0.14

-flat

-0.14

tap

-0.14

adies

-0.14

POSITIVE LOGITS

iveness

0.15

.AppendFormat

0.15

lia

0.15

Occurred

0.15

'na

0.14

èĢ

0.14

(SS

0.14

’na

0.14

criptor

0.14

 Hindered

0.14

Activations Density 0.004%

terms related to medical and scientific research, particularly in relation to cells, proteins, and psychological studies

No Comments

No Known Activations