INDEX

Explanations

references to tourism and travel activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

idence

-0.21

presso

-0.16

PCP

-0.15

endon

-0.15

andes

-0.15

ãĥĩãĤ£ãĤ¢

-0.14

sburg

-0.14

aren

-0.14

ī

-0.14

eland

-0.14

POSITIVE LOGITS

istic

0.28

neys

0.26

ney

0.25

ism

0.25

isted

0.23

isting

0.23

tour

0.22

isms

0.21

ist

0.21

bill

0.21

Activations Density 0.012%

references to tourism and travel activities

No Comments

No Known Activations