INDEX

Explanations

references to television series, particularly American sitcoms and their details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

bak

-0.15

 nIndex

-0.15

ycl

-0.15

ctal

-0.15

anean

-0.14

sw

-0.14

erten

-0.14

urtle

-0.14

ha

-0.14

sw

-0.14

POSITIVE LOGITS

eno

0.16

agit

0.16

acb

0.15

 tumble

0.15

PCP

0.15

ison

0.15

ÑĤÑĢÐ¾

0.15

PointerException

0.14

 TRANSACTION

0.14

rans

0.14

Activations Density 0.084%

references to television series, particularly American sitcoms and their details

No Comments

No Known Activations