INDEX

Explanations

event-related terms and attendance opportunities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ave

-0.19

AVE

-0.16

.connector

-0.15

coni

-0.15

 passive

-0.15

ocity

-0.15

inati

-0.14

Ð¸Ð¼Ð²

-0.13

 gamm

-0.13

otts

-0.13

POSITIVE LOGITS

izen

0.17

.IContainer

0.16

 Huffman

0.14

ãĥ³ãĥķ

0.14

izens

0.14

uces

0.14

AtPath

0.14

istrict

0.14

mites

0.14

ContentSize

0.14

Activations Density 0.041%

event-related terms and attendance opportunities

No Comments

No Known Activations