INDEX

Explanations

references to Harley Davidson motorcycles and related events or features

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

ulum

-0.17

_IB

-0.17

ilim

-0.16

éĮ

-0.15

Å¥

-0.15

_ib

-0.15

RIX

-0.14

ìĹ´

-0.14

rador

-0.14

.extern

-0.14

POSITIVE LOGITS

 Harley

0.31

 Scre

0.20

 Davidson

0.19

 Milwaukee

0.18

 Wisconsin

0.18

HAR

0.17

Har

0.16

Har

0.16

 Riding

0.16

Street

0.15

Activations Density 0.004%

references to Harley Davidson motorcycles and related events or features

No Comments

No Known Activations