INDEX

Explanations

concepts related to boundaries and community structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 æĻ´

-0.14

 ngang

-0.14

Ð²Ð°Ð¶

-0.13

 phÃŃa

-0.13

unkt

-0.13

reff

-0.13

 xong

-0.13

erdem

-0.13

errat

-0.13

 przypad

-0.12

POSITIVE LOGITS

 bounds

0.60

 confines

0.59

 boundaries

0.57

 borders

0.50

 limits

0.50

 walls

0.44

 scope

0.42

bounds

0.41

 Bounds

0.41

 parameters

0.40

Activations Density 0.160%

concepts related to boundaries and community structures

No Comments

No Known Activations