INDEX

Explanations

punctuation marks and expressions of excitement or emphasis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

Î±Î½Î¬

-0.15

 special

-0.15

oust

-0.14

 label

-0.14

 answer

-0.13

USTER

-0.13

azzo

-0.13

 Williamson

-0.13

 superv

-0.13

ired

-0.13

POSITIVE LOGITS

 LOVE

0.17

 Such

0.17

 SUCH

0.17

ovice

0.17

 loved

0.16

æĦĽ

0.16

HI

0.15

 love

0.15

 such

0.15

 noqa

0.15

Activations Density 0.018%

punctuation marks and expressions of excitement or emphasis

No Comments

No Known Activations