INDEX

Explanations

references to various types of vehicles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ships

-0.24

ship

-0.20

SHIP

-0.18

aires

-0.18

naire

-0.17

itzer

-0.16

gers

-0.15

naires

-0.15

urn

-0.15

ively

-0.15

POSITIVE LOGITS

riages

0.27

ibbean

0.24

è¾Ĩ

0.23

abin

0.21

pool

0.20

/people

0.20

oten

0.20

load

0.19

ä¸¡

0.18

/train

0.18

Activations Density 0.043%

references to various types of vehicles

No Comments

No Known Activations