INDEX

Explanations

numerical codes or identifiers related to various classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

-0.17

 Picker

-0.16

-0.15

 RectTransform

-0.15

 ÑĪÑĤ

-0.14

mar

-0.14

 care

-0.14

Fit

-0.14

eki

-0.14

 Ð¼Ð¸Ð»

-0.14

POSITIVE LOGITS

ollo

0.15

een

0.15

 Ø§ØªØŃØ§Ø¯

0.14

renom

0.14

iris

0.14

è©±

0.14

Exposed

0.14

-thumbnails

0.14

uell

0.14

/tutorial

0.14

Activations Density 0.010%

numerical codes or identifiers related to various classifications

No Comments

No Known Activations