INDEX

Explanations

references to enumerations and quantities in a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ural

-0.14

riel

-0.14

antu

-0.14

assa

-0.14

igg

-0.14

nice

-0.14

ellas

-0.13

ound

-0.13

eco

-0.13

itz

-0.13

POSITIVE LOGITS

ationally

0.16

file

0.15

UNET

0.15

 SceneManager

0.15

éļľ

0.14

imson

0.13

.Dot

0.13

oppable

0.13

 Profession

0.13

encion

0.13

Activations Density 0.037%

references to enumerations and quantities in a text

No Comments

No Known Activations