INDEX

Explanations

function definitions in programming code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ahlen

-0.14

ti

-0.14

æĭ¬

-0.14

 Elim

-0.14

-transform

-0.14

NAS

-0.13

NAS

-0.13

odom

-0.13

cmp

-0.13

POSITIVE LOGITS

rys

0.16

esthes

0.15

iversite

0.13

 Perf

0.13

ëĲĺ

0.13

toi

0.13

sand

0.13

izu

0.13

ohl

0.13

thren

0.13

Activations Density 0.042%

function definitions in programming code

No Comments

No Known Activations