INDEX

Explanations

symbols or non-alphanumeric characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

eton

-0.18

áº£y

-0.17

æĢ§

-0.15

ingleton

-0.14

 Podle

-0.14

ledon

-0.14

Ð²Ð¸Ð¶

-0.14

Ð¼Ð¾Ñģ

-0.14

ÑĢÑĥÐ¿

-0.14

dge

-0.14

POSITIVE LOGITS

akan

0.16

er

0.16

anine

0.15

ele

0.14

 Viet

0.14

anas

0.14

rob

0.14

alette

0.14

fortunately

0.14

Activations Density 0.073%

symbols or non-alphanumeric characters

No Comments

No Known Activations