INDEX

Explanations

location names and geographical identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

indic

-0.15

 Inherits

-0.14

Â¶

-0.13

 twice

-0.13

#'

-0.13

neh

-0.12

 infected

-0.12

\$

-0.12

 Ø²Ùħ

-0.12

POSITIVE LOGITS

-based

0.21

-Based

0.19

based

0.18

 based

0.18

-(

0.18

.–

0.17

 headquartered

0.17

//-

0.17

_based

0.17

(PR

0.17

Activations Density 0.036%

location names and geographical identifiers

No Comments

No Known Activations