INDEX

Explanations

code-related elements and structures, particularly those involving assignments and function definitions

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

eydi

-0.16

wis

-0.15

ĵåĲį

-0.15

 mell

-0.14

ltk

-0.13

Var

-0.13

("

-0.13

NamedQuery

-0.13

[contains

-0.13

Evidence

-0.13

POSITIVE LOGITS

 function

0.31

 async

0.29

async

0.28

()

0.26

function

0.26

()=>{↵

0.23

($)

0.21

({

0.21

(_)

0.21

 ()=>{↵

0.20

Activations Density 0.098%

code-related elements and structures, particularly those involving assignments and function definitions

No Comments

No Known Activations