INDEX

Explanations

references to tools and frameworks related to technology and research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

éļª

-0.15

ãĥ¬ãĥ¼

-0.14

Ð¾Ð»ÑĮ

-0.14

ãĤ«ãĥ¼

-0.14

HING

-0.13

::-

-0.13

HORT

-0.13

ìĹĩ

-0.13

 numberWith

-0.13

ÙĬÙĩ

-0.13

POSITIVE LOGITS

ABC

0.15

 simply

0.15

thalm

0.14

VIP

0.14

phies

0.14

ento

0.14

Ã¼gen

0.13

Ã´t

0.13

 forget

0.13

unte

0.13

Activations Density 0.362%

references to tools and frameworks related to technology and research

No Comments

No Known Activations