INDEX

Explanations

phrases that provide contextual background or history for a topic

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ashi

-0.18

anou

-0.17

eya

-0.15

 Vault

-0.14

icket

-0.14

ä¹ĭä¸Ģ

-0.14

rat

-0.14

atab

-0.14

acz

-0.14

api

-0.14

POSITIVE LOGITS

ffen

0.16

SKI

0.15

ipur

0.15

kaar

0.15

ivos

0.15

oksen

0.14

fad

0.14

ogan

0.14

Brief

0.14

icho

0.14

Activations Density 0.305%

phrases that provide contextual background or history for a topic

No Comments

No Known Activations