INDEX

Explanations

function definitions and related parameters 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 @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

agit

-0.14

reon

-0.14

AGER

-0.14

agn

-0.14

hed

-0.14

ault

-0.14

resent

-0.13

Ú¯Ø±

-0.13

lander

-0.13

 Cher

-0.13

POSITIVE LOGITS

 thá»¥

0.15

=?,

0.14

Multiplier

0.14

.*,

0.14

/Resources

0.14

 JNIEnv

0.14

èįī

0.14

~,

0.14

Mun

0.13

 PROCUREMENT

0.13

Activations Density 0.105%

function definitions and related parameters in programming code

No Comments

No Known Activations