INDEX

Explanations

markers and elements associated with code or data structure definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

oran

-0.16

coni

-0.16

Ã³j

-0.15

owi

-0.15

Ð¸ÑĤÑĭ

-0.14

itel

-0.14

stad

-0.14

/html

-0.14

onis

-0.14

Tob

-0.13

POSITIVE LOGITS

sink

0.15

pitch

0.15

bbbb

0.14

inent

0.14

aab

0.13

hoot

0.13

à¤¿à¤¦

0.13

bate

0.13

anoia

0.13

okes

0.13

Activations Density 0.359%

markers and elements associated with code or data structure definitions

No Comments

No Known Activations