INDEX

Explanations

structured data formats and function definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

inski

-0.18

.sat

-0.15

otive

-0.15

é¬¼

-0.14

sat

-0.14

Interval

-0.14

ilet

-0.14

 interval

-0.14

itch

-0.14

col

-0.14

POSITIVE LOGITS

ulos

0.15

olis

0.15

erset

0.14

 Rack

0.14

ghan

0.14

ãģ£

0.14

à¤¨à¤²

0.14

station

0.14

elson

0.14

-alist

0.14

Activations Density 0.030%

structured data formats and function definitions

No Comments

No Known Activations