INDEX

Explanations

dates and numerical information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

 ÑĦÐ°Ñħ

-0.14

LEC

-0.14

escal

-0.14

.dirty

-0.14

 Ð¿Ð¾Ð´ÑħÐ¾Ð´

-0.13

Ð¾Ð³ÑĢÐ°

-0.13

ãĥ¼ãĥĨãĤ£

-0.13

usu

-0.13

 ÑĤÐµÐº

-0.13

 ÐĴÐµÐ»Ð¸Ðº

-0.13

POSITIVE LOGITS

ogy

0.16

-Sah

0.15

ugins

0.14

amura

0.14

dsp

0.14

ãĥ¼ãĥ³

0.14

(disposing

0.14

uiten

0.14

peer

0.14

ogne

0.13

Activations Density 0.000%

dates and numerical information

No Comments

No Known Activations