INDEX

Explanations

locations and settings related to coffee shops, restaurants, and public spaces

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

MIS

-0.15

apur

-0.15

 itself

-0.15

eldon

-0.15

amax

-0.14

cession

-0.14

oday

-0.14

iem

-0.13

/umd

-0.13

POSITIVE LOGITS

ober

0.17

bourne

0.16

ehler

0.15

ideo

0.15

ļ

0.14

JOB

0.14

luet

0.14

gew

0.13

Writes

0.13

 Weiner

0.13

Activations Density 0.240%

locations and settings related to coffee shops, restaurants, and public spaces

No Comments

No Known Activations