INDEX

Explanations

language that indicates evidence and support in arguments or claims

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

adle

-0.17

uck

-0.16

atin

-0.15

ives

-0.15

 Claud

-0.15

 Sims

-0.14

 plat

-0.14

erty

-0.14

otty

-0.14

 Barth

-0.14

POSITIVE LOGITS

ocache

0.16

andest

0.14

alu

0.14

emmel

0.14

olest

0.14

Unc

0.14

Ø¬ÙĪ

0.14

cola

0.14

çĮ

0.14

ç

0.14

Activations Density 0.458%

language that indicates evidence and support in arguments or claims

No Comments

No Known Activations