INDEX

Explanations

references to organizational structures or entities

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

volt

-0.16

iÄĩ

-0.16

å¼ķãģį

-0.15

 laut

-0.15

uns

-0.14

asca

-0.14

 bore

-0.14

raw

-0.14

POSITIVE LOGITS

spath

0.17

elps

0.15

Î¼Î¿Î½

0.14

æ¶

0.14

æ·

0.13

ÐµÑĢÐµÐ´

0.13

AccessType

0.13

ãĥ¢ãĥ³

0.13

usch

0.13

 QuÃ©

0.13

Activations Density 0.000%

references to organizational structures or entities

No Comments

No Known Activations