INDEX

Explanations

references to photographs or images

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ling

-0.17

mail

-0.16

abouts

-0.15

OwnProperty

-0.15

lichen

-0.15

uche

-0.15

kir

-0.15

 Treasure

-0.15

most

-0.15

den

-0.15

POSITIVE LOGITS

orias

0.15

Î¸Î·

0.15

journal

0.15

ARGIN

0.14

ynthesis

0.14

ckt

0.14

-inline

0.14

ynom

0.14

 settlement

0.14

inspection

0.14

Activations Density 0.011%

references to photographs or images

No Comments

No Known Activations