INDEX

Explanations

references to "vision" and related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

artment

-0.16

oru

-0.16

lsen

-0.16

isol

-0.15

western

-0.15

.binding

-0.15

Ð°Ð½Ð¸ÑĨ

-0.14

elier

-0.14

ãģ°

-0.14

press

-0.14

POSITIVE LOGITS

aries

0.36

ary

0.31

ARY

0.24

naire

0.22

naires

0.19

erate

0.18

ary

0.17

 quests

0.16

ervas

0.16

Activations Density 0.016%

references to "vision" and related concepts

No Comments

No Known Activations