INDEX

Explanations

abbreviations or acronyms related to organizational or genre classifications

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

ellation

-0.16

VERTISE

-0.15

_MAKE

-0.15

accom

-0.15

 latter

-0.14

ouch

-0.14

Ð¾Ð²Ð°ÑĢ

-0.14

iki

-0.14

AKER

-0.14

 accom

-0.13

POSITIVE LOGITS

htdocs

0.16

ripp

0.16

ihan

0.16

athe

0.15

ieves

0.15

ÄĻk

0.14

subtype

0.14

Ð»ÐºÐ¸

0.14

ylim

0.14

mtime

0.14

Activations Density 0.032%

abbreviations or acronyms related to organizational or genre classifications

No Comments

No Known Activations