INDEX

Explanations

references to local communities or local authorities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

Allocate

-0.16

iosa

-0.15

orque

-0.15

rell

-0.14

ogl

-0.14

arte

-0.14

(IT

-0.14

Ìĥ

-0.14

co

-0.13

POSITIVE LOGITS

vore

0.18

Ã¤h

0.15

lane

0.15

uchos

0.15

ÅĻez

0.14

eland

0.14

 chÃŃ

0.14

æĥł

0.14

alnÄ±z

0.14

IALIZED

0.14

Activations Density 0.012%

references to local communities or local authorities

No Comments

No Known Activations