INDEX

Explanations

references to images or visual content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 Gamb

-0.17

irit

-0.17

 Fallon

-0.16

ipur

-0.15

 residence

-0.15

urg

-0.14

ìľł

-0.14

 Conditioning

-0.14

 assim

-0.14

POSITIVE LOGITS

.twig

0.15

ndl

0.15

probe

0.15

eldo

0.14

antha

0.14

REA

0.14

jom

0.14

_mB

0.14

ÐµÑĤÐµÐ»ÑĮ

0.14

uncia

0.14

Activations Density 0.010%

references to images or visual content

No Comments

No Known Activations