INDEX

Explanations

references to specific individuals or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

kees

-0.16

olet

-0.16

igu

-0.15

tron

-0.15

utzer

-0.15

ound

-0.15

iolet

-0.15

.Experimental

-0.14

akes

-0.14

ogue

-0.14

POSITIVE LOGITS

sm

0.18

sein

0.18

 Angeles

0.16

mos

0.16

mium

0.16

ething

0.15

uke

0.15

elle

0.15

sw

0.15

 Briggs

0.14

Activations Density 0.039%

references to specific individuals or entities

No Comments

No Known Activations