INDEX

Explanations

references to specific events or occurrences related to wrestling and pop culture

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

ernals

-0.15

iedy

-0.14

avra

-0.14

oldt

-0.14

warts

-0.14

foy

-0.14

vant

-0.14

Ø±Ø§ÙĨÛĮ

-0.13

chas

-0.13

POSITIVE LOGITS

0.19

UDA

0.17

sdk

0.17

Cop

0.16

sar

0.15

Äĥr

0.15

sut

0.15

ska

0.15

cop

0.15

roit

0.15

Activations Density 0.146%

references to specific events or occurrences related to wrestling and pop culture

No Comments

No Known Activations