INDEX

Explanations

words related to geographic locations and specific cultural events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

Æ¯á»

-0.15

noch

-0.15

-unused

-0.14

 Truy

-0.14

ldb

-0.14

ural

-0.14

alles

-0.14

lok

-0.13

ãĢħ

-0.13

Å¡it

-0.13

POSITIVE LOGITS

-sama

0.15

ream

0.14

tin

0.14

 Equip

0.14

[assembly

0.14

dÃ¼k

0.14

oz

0.13

_{}

0.13

orte

0.13

 Savage

0.13

Activations Density 0.232%

words related to geographic locations and specific cultural events

No Comments

No Known Activations