INDEX

Explanations

references to historical events and artifacts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

Ð¾Ð±Ð¾Ð²

-0.20

-0.14

ekt

-0.14

ben

-0.14

ences

-0.13

ities

-0.13

á»ĩ

-0.13

 Stanton

-0.13

POSITIVE LOGITS

ÐĲÑĢÑħÑĸÐ²

0.19

âĦĸâĦĸ

0.19

ultan

0.16

apult

0.15

ichern

0.15

reesome

0.15

Ðµ

0.15

âĦĸ

0.15

_statuses

0.14

Byl

0.14

Activations Density 0.779%

references to historical events and artifacts

No Comments

No Known Activations