INDEX

Explanations

key action words and associated phrases that imply movement or transition in scenarios

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ÑİÐº

-0.15

 çĻ¾åº¦

-0.14

enko

-0.14

aft

-0.14

Ã¥n

-0.14

GMEM

-0.14

IVA

-0.14

sa

-0.14

è©ŀ

-0.14

 alliance

-0.14

POSITIVE LOGITS

lassen

0.15

iske

0.15

çħ§

0.14

lass

0.14

txn

0.13

 paddle

0.13

å¢ŀ

0.13

::_

0.13

 full

0.13

quette

0.13

Activations Density 0.029%

key action words and associated phrases that imply movement or transition in scenarios

No Comments

No Known Activations