INDEX

Explanations

keywords related to travel and geographic content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

atur

-0.17

ota

-0.15

Fur

-0.14

ÑĤÐ°

-0.14

htm

-0.14

Leo

-0.14

vore

-0.14

fur

-0.14

atura

-0.13

KER

-0.13

POSITIVE LOGITS

 Parkway

0.15

ãĥ©ãĤ¤ãĥ³

0.15

Ã¡tka

0.15

memberOf

0.14

__,__

0.14

iliz

0.14

é§

0.14

ideographic

0.14

èĲ½

0.14

.um

0.14

Activations Density 0.037%

keywords related to travel and geographic content

No Comments

No Known Activations