INDEX

Explanations

references to lighting elements

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

plorer

-0.15

å¯

-0.15

 modeling

-0.15

itten

-0.14

à¹Ĥà¸ŀ

-0.14

KL

-0.14

 Crab

-0.14

erus

-0.14

ActionResult

-0.13

POSITIVE LOGITS

ì²´

0.17

alth

0.15

och

0.14

chest

0.14

anto

0.14

 Ð²ÑĸÐ·

0.14

ung

0.13

lund

0.13

è¿ĳ

0.13

atab

0.13

Activations Density 0.001%

references to lighting elements

No Comments

No Known Activations