INDEX

Explanations

function declarations and invocations in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ariat

-0.16

vail

-0.15

oux

-0.14

wiÄħ

-0.14

Ã©l

-0.14

ruba

-0.14

aÃ§

-0.14

rouw

-0.13

cak

-0.13

ening

-0.13

POSITIVE LOGITS

_argument

0.24

.SOCK

0.18

.LENGTH

0.17

 NotSupportedException

0.16

è¾ĳ

0.16

	throws

0.16

summary

0.15

nil

0.15

 else

0.15

->_

0.15

Activations Density 0.164%

function declarations and invocations in code

No Comments

No Known Activations