INDEX

Explanations

a variety of significant numbers and data points in 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 @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

anske

-0.15

otime

-0.15

Ã´m

-0.15

tÃŃ

-0.14

_oper

-0.14

PFN

-0.14

meli

-0.14

.parser

-0.14

çļ

-0.14

 voks

-0.14

POSITIVE LOGITS

le

0.17

bservice

0.16

abb

0.15

 Marc

0.15

ony

0.15

lever

0.14

LE

0.14

iÄĻ

0.14

rc

0.14

oks

0.14

Activations Density 0.012%

a variety of significant numbers and data points in the text

No Comments

No Known Activations