INDEX

Explanations

quoted names and phrases

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

ernen

-0.15

ä½Ĳ

-0.15

REFERENCE

-0.14

setSize

-0.14

ht

-0.14

agrams

-0.14

ervlet

-0.14

htt

-0.14

elves

-0.14

Cached

-0.14

POSITIVE LOGITS

olta

0.14

oi

0.14

otu

0.14

ads

0.14

 Operators

0.14

Ð¾Ð³Ð°

0.14

ãĥ¼ãĤ¹

0.13

zee

0.13

 Ð²Ð¾Ð·ÑĢÐ°ÑģÑĤÐ°

0.13

oad

0.13

Activations Density 0.177%

quoted names and phrases

No Comments

No Known Activations