INDEX

Explanations

instances of high-value or significant numerical data within the context of narratives or reports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

itch

-0.17

Rag

-0.17

ITCH

-0.17

ambi

-0.16

crit

-0.16

UIT

-0.15

amble

-0.14

icit

-0.14

amb

-0.14

¶ļ

-0.13

POSITIVE LOGITS

deen

0.16

ares

0.16

asca

0.15

ãĤ¤ãĤº

0.14

_CN

0.14

anim

0.14

hus

0.14

sey

0.14

alled

0.13

è¯ļ

0.13

Activations Density 0.003%

instances of high-value or significant numerical data within the context of narratives or reports

No Comments

No Known Activations

instances of high-value or significant numerical data within the context of narratives or reports

No Comments

No Known Activations