INDEX

Explanations

punctuation and formatting elements in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ROM

-0.15

	TokenName

-0.15

à¸²à¸©à¸İ

-0.13

 âĢķ

-0.13

TRGL

-0.12

YYS

-0.12

EMPLARY

-0.12

RTE

-0.12

okoj

-0.12

 conveniently

-0.12

POSITIVE LOGITS

à¸Ĺ

0.24

à¸ª

0.23

à¸Ħ

0.23

à¸Ĥ

0.23

à¸ļ

0.23

à¸¡

0.22

à¸Ķ

0.22

à¸Ĭ

0.22

à¸ģ

0.21

à¸§

0.21

Activations Density 0.009%

punctuation and formatting elements in text

No Comments

No Known Activations