INDEX

Explanations

references to physical items and their usage in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

osi

-0.16

olla

-0.16

eca

-0.14

Pun

-0.14

avig

-0.14

gon

-0.14

Fry

-0.14

ipop

-0.14

yna

-0.14

xfa

-0.13

POSITIVE LOGITS

uling

0.17

ieres

0.17

resizing

0.14

veÃ§

0.14

udder

0.14

elor

0.14

unes

0.14

leme

0.14

otes

0.14

uin

0.14

Activations Density 0.012%

references to physical items and their usage in various contexts

No Comments

No Known Activations