INDEX

Explanations

phrases related to navigation and directions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

bek

-0.17

Ã¸d

-0.16

JT

-0.15

abil

-0.15

lio

-0.14

awan

-0.14

ÑĭÐ¿

-0.13

ennie

-0.13

 voll

-0.13

ables

-0.13

POSITIVE LOGITS

emplate

0.15

Ignore

0.15

OfType

0.14

 Resume

0.14

ê¶ģ

0.14

uhn

0.14

 ØµØ±Ùģ

0.14

.Orientation

0.13

nicas

0.13

ÅĪ

0.13

Activations Density 0.002%

phrases related to navigation and directions

No Comments

No Known Activations