INDEX

Explanations

phrases related to elimination or removal

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

_YUV

-0.16

_activate

-0.14

ARP

-0.14

ertest

-0.14

ockey

-0.14

-tip

-0.14

inja

-0.14

 Roll

-0.14

ublik

-0.13

ablo

-0.13

POSITIVE LOGITS

ucken

0.20

oyal

0.17

æģ¯

0.17

ynes

0.16

edla

0.16

ubes

0.15

ittings

0.15

gang

0.15

ugal

0.14

uide

0.14

Activations Density 0.011%

phrases related to elimination or removal

No Comments

No Known Activations