INDEX

Explanations

mentions of the name "Johns Hopkins."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

pin

-0.16

Ð±Ð¾Ð»

-0.16

zÃŃ

-0.15

oct

-0.15

wend

-0.15

amel

-0.14

ergy

-0.14

/Edit

-0.14

aille

-0.14

_bn

-0.14

POSITIVE LOGITS

 Hopkins

0.33

Hop

0.21

hop

0.19

_hop

0.19

onical

0.19

-hop

0.16

enek

0.15

 hops

0.15

 Johns

0.15

eneg

0.14

Activations Density 0.005%

mentions of the name "Johns Hopkins."

No Comments

No Known Activations

mentions of the name "Johns Hopkins."

No Comments

No Known Activations