INDEX

Explanations

references to television show seasons and renewals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ippi

-0.16

atti

-0.16

urr

-0.15

IEWS

-0.15

ur

-0.15

ellers

-0.14

urf

-0.14

atern

-0.14

urd

-0.14

uros

-0.14

POSITIVE LOGITS

.scalablytyped

0.20

ÑħÐ¾Ð²

0.17

/Branch

0.15

buch

0.14

#af

0.14

vertime

0.14

ousand

0.14

ODO

0.14

gamber

0.14

CONDS

0.13

Activations Density 0.020%

references to television show seasons and renewals

No Comments

No Known Activations