INDEX

Explanations

references to temporary variables or temporary states within programming context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

meni

-0.15

-0.14

earn

-0.14

usat

-0.14

uche

-0.13

errar

-0.13

dez

-0.13

quete

-0.13

ensed

-0.13

POSITIVE LOGITS

Ùĩ

0.15

ï¿¥

0.15

Ð¾ÑĩÐ½Ð¾

0.14

íģ¼

0.14

 Daly

0.14

 divider

0.14

ISODE

0.14

Ã©v

0.14

ìļķ

0.14

ABCDEFGHIJKLMNOP

0.14

Activations Density 0.005%

references to temporary variables or temporary states within programming context

No Comments

No Known Activations