INDEX

Explanations

mentions of memory and storage specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

PTS

-0.16

illac

-0.16

ivet

-0.16

 Charter

-0.16

dez

-0.15

 Roller

-0.15

cala

-0.15

 showc

-0.15

 ì¶ľìŀ¥

-0.15

 kapÄ±

-0.14

POSITIVE LOGITS

 memory

0.34

DDR

0.30

DIM

0.29

 Memory

0.29

 sticks

0.29

RAM

0.28

 modules

0.28

 Kingston

0.28

memory

0.27

Memory

0.27

Activations Density 0.004%

mentions of memory and storage specifications

No Comments

No Known Activations