INDEX

Explanations

references to academic sources or citations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 Dispose

-0.14

tua

-0.14

 Mane

-0.14

 Woods

-0.14

aut

-0.14

 families

-0.13

zon

-0.13

 mean

-0.13

illin

-0.13

POSITIVE LOGITS

.rl

0.15

GuidId

0.15

lÃ¼

0.14

bson

0.14

umlu

0.14

eyJ

0.14

 Crescent

0.14

ØªØ²

0.14

 ê¸°íĥĢ

0.14

 TCHAR

0.14

Activations Density 0.021%

references to academic sources or citations

No Comments

No Known Activations