INDEX

Explanations

references to gates and entries

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

onth

-0.17

(æ°´

-0.15

ĺìĿ´

-0.14

 Renders

-0.14

icone

-0.14

ertz

-0.14

.DOWN

-0.14

rada

-0.13

Pap

-0.13

à¸¸à¸¡

-0.13

POSITIVE LOGITS

 wire

0.16

wire

0.15

 Slut

0.14

Î¹Î¬

0.14

arme

0.14

vp

0.14

-chevron

0.14

InBackground

0.13

Tak

0.13

Activations Density 0.015%

references to gates and entries

No Comments

No Known Activations