INDEX

Explanations

terms related to pavilions or similar structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

icy

-0.15

Ð¾ÑĩÐµÐº

-0.14

á»Ł

-0.13

 nghiá»ĩm

-0.13

idy

-0.13

uition

-0.13

POSITIVE LOGITS

tak

0.17

bilt

0.17

BUM

0.15

agas

0.15

#!

0.15

ê¹

0.15

ãĤīãģļ

0.15

EPHIR

0.14

laps

0.14

rava

0.14

Activations Density 0.004%

terms related to pavilions or similar structures

No Comments

No Known Activations