INDEX

Explanations

references to activities or events occurring throughout the entire year

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

asso

-0.17

ania

-0.16

olia

-0.15

avl

-0.15

_TUN

-0.15

ÑĢÐ°Ð¶

-0.15

oli

-0.15

agal

-0.15

Ĺ

-0.14

íĹĮ

-0.14

POSITIVE LOGITS

Ã©li

0.15

 petites

0.14

ths

0.14

 Isis

0.14

 padded

0.14

ergus

0.13

ssc

0.13

ì§ĳ

0.13

 Bryant

0.13

Activations Density 0.009%

references to activities or events occurring throughout the entire year

No Comments

No Known Activations