INDEX

Explanations

references to roles and experiences in professional contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ossal

-0.18

opia

-0.17

 Kant

-0.15

brero

-0.15

 gust

-0.15

addtogroup

-0.14

iami

-0.14

ernaut

-0.14

uien

-0.14

POSITIVE LOGITS

elle

0.14

inus

0.14

zier

0.14

asz

0.14

eced

0.14

xin

0.13

 Larson

0.13

 lagi

0.13

iki

0.13

Activations Density 0.495%

references to roles and experiences in professional contexts

No Comments

No Known Activations