INDEX

Explanations

references to records or documentation related to employees, business operations, and health or social issues

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

å·®

-0.15

obi

-0.15

Ã©lÃ©

-0.14

ong

-0.14

ynam

-0.14

SuppressLint

-0.14

ì§¸

-0.14

iales

-0.14

 Fischer

-0.14

 convention

-0.13

POSITIVE LOGITS

.mybatisplus

0.15

patibility

0.15

agnar

0.14

inode

0.14

unker

0.13

 ëª¨ìĬµ

0.13

anch

0.13

pte

0.13

.poi

0.13

Activations Density 0.471%

references to records or documentation related to employees, business operations, and health or social issues

No Comments

No Known Activations