INDEX

Explanations

times and specific scheduling details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ä¼

-0.16

 Sund

-0.15

ANGO

-0.15

opis

-0.15

sez

-0.14

Ø§Ø¬Ø§Øª

-0.14

è¤

-0.14

èĤ¥

-0.13

ser

-0.13

:"-"`↵

-0.13

POSITIVE LOGITS

zzo

0.17

mares

0.16

ein

0.16

Pros

0.14

zÄħ

0.14

zilla

0.14

assed

0.14

 PATCH

0.14

-animate

0.13

nings

0.13

Activations Density 0.012%

times and specific scheduling details

No Comments

No Known Activations