INDEX

Explanations

references to images and visual content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ebo

-0.15

rippling

-0.15

ulta

-0.15

ìĽĥ

-0.15

redo

-0.14

Insensitive

-0.14

eteria

-0.14

 subt

-0.14

enas

-0.14

 salute

-0.14

POSITIVE LOGITS

 stocks

0.18

 graphics

0.17

 choices

0.17

graphics

0.15

 Stocks

0.15

 Choices

0.15

stocks

0.15

llib

0.15

 nrows

0.14

 tuned

0.14

Activations Density 0.049%

references to images and visual content

No Comments

No Known Activations