INDEX

Explanations

questions and inquiries expressed with question marks

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

opoulos

-0.15

andez

-0.15

dil

-0.14

Ø§ÙħØ§

-0.14

ample

-0.14

Ĩ

-0.13

gard

-0.13

ascar

-0.13

/package

-0.13

.="

-0.13

POSITIVE LOGITS

udos

0.15

anyl

0.15

à¹Ĩ

0.15

ëĭĿ

0.15

eh

0.15

arium

0.14

echa

0.14

lÃ¡

0.14

 *)((

0.14

rim

0.14

Activations Density 0.100%

questions and inquiries expressed with question marks

No Comments

No Known Activations