INDEX

Explanations

terms related to motor vehicles and related activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

urement

-0.18

eners

-0.17

edy

-0.17

á»ĩnh

-0.17

nown

-0.17

 Ware

-0.16

lef

-0.16

WARE

-0.15

otropic

-0.15

ures

-0.15

POSITIVE LOGITS

ized

0.16

amedi

0.16

Ø®Ø§ÙĨÙĩ

0.15

icing

0.15

ically

0.15

SI

0.14

astro

0.14

idade

0.14

logy

0.14

Activations Density 0.025%

terms related to motor vehicles and related activities

No Comments

No Known Activations