INDEX

Explanations

instructions related to cooking or food preparation steps

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

ForResource

-0.16

lian

-0.16

ousand

-0.15

sec

-0.15

ItemAt

-0.15

eyer

-0.15

ustin

-0.14

InSection

-0.14

ev

-0.14

rive

-0.14

POSITIVE LOGITS

 highlights

0.17

.mozilla

0.14

anut

0.14

 highlight

0.14

Ã¡ch

0.14

endum

0.14

eries

0.14

 ÐĽÑĥÑĩ

0.14

0.13

 judgments

0.13

Activations Density 0.025%

instructions related to cooking or food preparation steps

No Comments

No Known Activations