INDEX

Explanations

words related to cars and vehicles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

gers

-0.18

ships

-0.17

ively

-0.17

etter

-0.15

atility

-0.15

hips

-0.15

QUIRE

-0.14

ayed

-0.14

esser

-0.14

itzer

-0.14

POSITIVE LOGITS

riages

0.35

pool

0.32

ibbean

0.32

è¾Ĩ

0.24

abin

0.24

sharing

0.24

load

0.23

riage

0.23

avan

0.23

ä¸¡

0.22

Activations Density 0.042%

words related to cars and vehicles

No Comments

No Known Activations