INDEX

Explanations

conversational structures and dialogue markers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

Damn

-0.16

akat

-0.15

inis

-0.14

uche

-0.14

 seam

-0.14

Ð¾Ð»ÐµÐµ

-0.14

ingers

-0.13

èĤ¥

-0.13

Yep

-0.13

 distinct

-0.13

POSITIVE LOGITS

 come

0.20

 Listen

0.20

Exc

0.20

 Come

0.20

Listen

0.20

You

0.19

 look

0.19

listen

0.19

 Look

0.19

 listen

0.18

Activations Density 0.303%

conversational structures and dialogue markers

No Comments

No Known Activations