INDEX

Explanations

references to "mortar" and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

eners

-0.17

.qq

-0.16

verter

-0.15

ondere

-0.15

olver

-0.15

oss

-0.15

istor

-0.14

yl

-0.14

adoo

-0.14

Acts

-0.14

POSITIVE LOGITS

Äįet

0.15

Ð¾ÐºÐ¾Ð½

0.14

ÏģÎ±ÏĤ

0.14

vk

0.14

Î¯Î´Î±

0.13

.Flags

0.13

ÅĻes

0.13

_BACKEND

0.13

 ÑĩÑĥÐ¶

0.13

ustin

0.13

Activations Density 0.006%

references to "mortar" and related terms

No Comments

No Known Activations