INDEX

Explanations

references to letters and written communication

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

ot

-0.15

fri

-0.14

ara

-0.14

yum

-0.14

opsis

-0.14

 gridColumn

-0.14

xing

-0.13

lemn

-0.13

lay

-0.13

yn

-0.13

POSITIVE LOGITS

rops

0.16

press

0.15

ores

0.15

ToDevice

0.15

ICENSE

0.15

ÅĻ

0.15

boxed

0.15

tres

0.14

prites

0.14

annis

0.14

Activations Density 0.016%

references to letters and written communication

No Comments

No Known Activations