INDEX

Explanations

geographic and distance-related information

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

isci

-0.17

GetSize

-0.16

Ã¸r

-0.15

gor

-0.15

vertisement

-0.15

(OP

-0.15

gin

-0.15

rimp

-0.15

Ã´n

-0.15

.Mock

-0.14

POSITIVE LOGITS

eref

0.15

0.14

ppe

0.14

anh

0.13

hb

0.13

 toll

0.13

/frontend

0.13

 sett

0.13

Activations Density 0.031%

geographic and distance-related information

No Comments

No Known Activations