INDEX

Explanations

references to warriors and concepts related to courage or combat

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

iddi

-0.15

ovah

-0.15

ãģ«åħ¥

-0.14

serter

-0.14

adoo

-0.14

ilim

-0.14

eko

-0.14

sob

-0.14

lict

-0.14

eing

-0.14

POSITIVE LOGITS

ette

0.15

umeric

0.14

ften

0.14

etti

0.14

accine

0.13

ampion

0.13

uw

0.13

aphael

0.13

holds

0.13

etten

0.13

Activations Density 0.003%

references to warriors and concepts related to courage or combat

No Known Activations