INDEX

Explanations

affirmative statements or expressions of agreement

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

 throws

-0.15

ayd

-0.14

 @"↵

-0.14

endregion

-0.14

atch

-0.14

.HandlerFunc

-0.14

enco

-0.14

ĵ¨

-0.14

dut

-0.13

 authorised

-0.13

POSITIVE LOGITS

Ð³Ð»

0.16

ewis

0.15

AllWindows

0.15

ycastle

0.14

antro

0.14

acija

0.14

ãĥ³ãĥ

0.14

ÑħÐ¸

0.14

 manner

0.14

dll

0.14

Activations Density 0.000%

affirmative statements or expressions of agreement

No Comments

No Known Activations