INDEX

Explanations

technical references and terms related to programming or legal agreements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

áº¯t

-0.15

uide

-0.14

_UNUSED

-0.14

Ø§Ø¹

-0.14

-in

-0.14

Stencil

-0.13

 canned

-0.13

à¥ģà¤ľ

-0.13

 Opposition

-0.13

Opacity

-0.13

POSITIVE LOGITS

cker

0.18

ÑıÐ½

0.16

Ð¸Ð¼Ñĥ

0.16

ulado

0.15

inium

0.15

izyon

0.15

 stretch

0.15

shal

0.14

dle

0.14

anvas

0.14

Activations Density 0.003%

technical references and terms related to programming or legal agreements

No Comments

No Known Activations