INDEX

Explanations

parenthetical expressions or references to measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

 Crawford

-0.15

yor

-0.15

arent

-0.15

iju

-0.15

-0.14

VER

-0.14

Ã¼hl

-0.14

 cdecl

-0.14

orer

-0.14

POSITIVE LOGITS

essian

0.16

<*>

0.14

ãĥ£

0.14

.iso

0.14

.jasper

0.14

ervo

0.14

 spheres

0.13

Cyr

0.13

.Attribute

0.13

ì¹¨

0.13

Activations Density 0.029%

parenthetical expressions or references to measurements

No Comments

No Known Activations