INDEX

Explanations

references to applications and tools for various functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

lose

-0.15

igner

-0.15

 Coverage

-0.15

hores

-0.14

Coverage

-0.14

rippling

-0.14

çº¿

-0.14

dispose

-0.13

edor

-0.13

ughs

-0.13

POSITIVE LOGITS

let

0.23

 letting

0.22

 lets

0.20

 collect

0.20

 automatically

0.20

 tracks

0.18

 help

0.18

 Collect

0.18

help

0.18

 helps

0.17

Activations Density 0.225%

references to applications and tools for various functions

No Comments

No Known Activations