INDEX

Explanations

the preposition "in" as an indicator of location

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

coon

-0.18

elman

-0.17

bao

-0.15

anson

-0.15

abra

-0.15

wish

-0.15

ropol

-0.15

FFE

-0.14

ductor

-0.14

apult

-0.14

POSITIVE LOGITS

èİ

0.16

zc

0.16

Bel

0.15

.vars

0.15

Ń

0.14

 Rubio

0.14

0.13

anni

0.13

ninger

0.13

Activations Density 0.021%

the preposition "in" as an indicator of location

No Comments

No Known Activations