INDEX

Explanations

bibliographic references and citations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

 Sloan

-0.15

orian

-0.14

á¿ĸ

-0.14

pirit

-0.14

uter

-0.14

Hue

-0.14

RY

-0.14

kinson

-0.13

hei

-0.13

 Futures

-0.13

POSITIVE LOGITS

iero

0.16

 INLINE

0.15

aeper

0.14

.pretty

0.14

á»Ļng

0.14

agog

0.14

 Cable

0.14

stav

0.14

izik

0.14

acos

0.14

Activations Density 0.052%

bibliographic references and citations

No Comments

No Known Activations