INDEX

Explanations

references to structures or systems, particularly in a programming or organizational context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

-0.17

Ã´ng

-0.15

 Human

-0.14

igue

-0.14

 human

-0.14

glas

-0.14

ossa

-0.14

 course

-0.14

avian

-0.13

POSITIVE LOGITS

erap

0.16

ieri

0.16

senal

0.15

 sÃłng

0.14

.IsNullOr

0.14

ewan

0.14

ull

0.14

 Affero

0.14

ahl

0.14

ancellor

0.14

Activations Density 0.010%

references to structures or systems, particularly in a programming or organizational context

No Comments

No Known Activations