INDEX

Explanations

punctuation marks and their placement within text

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

stoff

-0.15

ubat

-0.15

emens

-0.14

 AXIS

-0.14

lander

-0.14

Brun

-0.14

ie

-0.14

ulen

-0.14

ault

-0.14

POSITIVE LOGITS

oir

0.15

amas

0.15

alted

0.15

ipsis

0.15

ilir

0.14

Ø¹Ø¯Ø§Ø¯

0.14

ovali

0.14

ulp

0.14

.MixedReality

0.14

.projects

0.14

Activations Density 0.022%

punctuation marks and their placement within text

No Comments

No Known Activations