INDEX

Explanations

prominent names or titles associated with specific entities or organizations

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

imes

-0.17

ster

-0.17

ero

-0.15

 boiler

-0.15

 subs

-0.15

ä¿

-0.14

tar

-0.14

 pitched

-0.14

 Alfred

-0.14

 Gang

-0.13

POSITIVE LOGITS

-SA

0.15

REAK

0.14

é¸¡

0.14

OSH

0.14

agra

0.14

Äįer

0.14

uche

0.14

 McMahon

0.14

.lst

0.14

ourse

0.14

Activations Density 0.251%

prominent names or titles associated with specific entities or organizations

No Comments

No Known Activations