INDEX

Explanations

entities related to leadership and authority figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

alter

-0.17

ushman

-0.17

 geÃ§

-0.15

.nlm

-0.15

enge

-0.15

elter

-0.15

tery

-0.14

ITER

-0.14

Alter

-0.14

nice

-0.14

POSITIVE LOGITS

oli

0.17

æĸĹ

0.15

½

0.15

anium

0.15

Lo

0.15

ritten

0.14

á»ķ

0.14

lein

0.14

olo

0.14

oria

0.14

Activations Density 0.026%

entities related to leadership and authority figures

No Comments

No Known Activations