INDEX

Explanations

specific terms and abbreviations that indicate classifications or categories

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

dik

-0.16

odega

-0.16

opal

-0.15

aucoup

-0.14

edback

-0.14

à¤¿à¤µà¤°

-0.14

/***/

-0.13

ayah

-0.13

.setAuto

-0.13

.wp

-0.13

POSITIVE LOGITS

Ð»Ð°Ð³Ð°

0.14

 Kling

0.14

uff

0.14

 Fleming

0.14

ulled

0.14

 darauf

0.14

 innoc

0.13

Î´Î¬

0.13

èĩ´

0.13

.yaml

0.13

Activations Density 0.072%

specific terms and abbreviations that indicate classifications or categories

No Comments

No Known Activations