INDEX

Explanations

references to various types of automobiles 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 @ 8-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

itzer

-0.16

WARE

-0.15

oria

-0.15

edy

-0.15

ellery

-0.15

naire

-0.14

AYOUT

-0.14

edor

-0.14

inct

-0.14

orian

-0.14

POSITIVE LOGITS

ibbean

0.21

riages

0.20

avana

0.17

abin

0.17

scape

0.16

afe

0.16

lia

0.16

ocker

0.16

pool

0.15

illon

0.15

Activations Density 0.073%

references to various types of automobiles and vehicles

No Comments

No Known Activations