INDEX

Explanations

occurrences of punctuation and formatting elements within the text

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

å¤«

-0.15

ierz

-0.15

 Cunning

-0.15

ÑĢÐµÐ¶

-0.15

olute

-0.15

ÑģÐ¸Ð¾Ð½

-0.15

èĥİ

-0.14

ÐµÐ½Ð¸Ð¸

-0.14

ewise

-0.14

upakan

-0.14

POSITIVE LOGITS

rou

0.16

0.15

pov

0.13

 Need

0.13

rod

0.13

AAA

0.13

SYS

0.13

/Gate

0.13

Atlas

0.13

Mis

0.13

Activations Density 0.031%

occurrences of punctuation and formatting elements within the text

No Comments

No Known Activations