INDEX

Explanations

intensifiers that convey strong emphasis or importance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

uzzi

-0.15

 Heads

-0.15

ReuseIdentifier

-0.15

ivor

-0.14

pling

-0.14

icator

-0.14

 Chaos

-0.13

BSD

-0.13

avanaugh

-0.13

assa

-0.13

POSITIVE LOGITS

ieber

0.19

ont

0.16

 Gund

0.15

 Claus

0.15

essen

0.15

xo

0.14

 filtr

0.14

ÐµÑı

0.14

.datab

0.14

-static

0.14

Activations Density 0.029%

intensifiers that convey strong emphasis or importance

No Comments

No Known Activations