INDEX

Explanations

references to educational programs and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

iverse

-0.13

 quáº§n

-0.13

 Pier

-0.13

Gatt

-0.13

ByKey

-0.13

enda

-0.13

ATTR

-0.13

POSITIVE LOGITS

awe

0.16

 ãĥ¯

0.15

upal

0.15

 uchar

0.15

apes

0.14

rema

0.14

lisi

0.13

mouseover

0.13

clc

0.13

achs

0.13

Activations Density 0.273%

references to educational programs and organizations

No Comments

No Known Activations