INDEX

Explanations

references to web pages and their attributes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

self

-0.17

ly

-0.16

igo

-0.16

redd

-0.15

 apparent

-0.15

reds

-0.15

.LENGTH

-0.14

epad

-0.14

wner

-0.14

igation

-0.14

POSITIVE LOGITS

illisecond

0.15

antry

0.15

chedulers

0.14

Ð½ÐµÐ·

0.14

bilt

0.14

iology

0.14

SocketAddress

0.14

views

0.14

uliar

0.14

ÐĴÐĲ

0.14

Activations Density 0.040%

references to web pages and their attributes

No Comments

No Known Activations