INDEX

Explanations

references to dates and timelines

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 Ð²Ð¾ÑĤ

-0.15

reuse

-0.14

.localized

-0.14

 Rosenberg

-0.14

unic

-0.13

.optString

-0.13

ãĥĥãĤ«ãĥ¼

-0.13

lover

-0.13

Carthy

-0.13

 vars

-0.13

POSITIVE LOGITS

ÐĽÐĲ

0.17

Î¸Î¿

0.17

DTD

0.14

ëŀĻ

0.13

avr

0.13

 tiener

0.13

 Outlet

0.13

zzo

0.13

ccount

0.13

chein

0.13

Activations Density 0.021%

references to dates and timelines

No Comments

No Known Activations