INDEX

Explanations

references to names and personal acknowledgments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

eron

-0.16

nod

-0.15

è¨ª

-0.15

lik

-0.14

rite

-0.14

TEX

-0.14

 Brands

-0.13

ono

-0.13

League

-0.13

ilk

-0.13

POSITIVE LOGITS

ØºÙħ

0.16

bach

0.15

strup

0.15

agus

0.15

gaz

0.15

undi

0.15

aliz

0.14

ende

0.14

allest

0.14

Activations Density 0.038%

references to names and personal acknowledgments

No Comments

No Known Activations