INDEX

Explanations

references to cards and related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ledi

-0.19

ously

-0.17

inÃ§

-0.17

OUS

-0.17

ĺìĿ´

-0.17

estone

-0.16

onders

-0.16

ous

-0.16

tings

-0.15

ander

-0.15

POSITIVE LOGITS

inality

0.27

holder

0.25

igan

0.22

holders

0.22

inals

0.21

inal

0.21

.Card

0.21

INAL

0.20

/Card

0.17

nett

0.17

Activations Density 0.037%

references to cards and related terminology

No Comments

No Known Activations