INDEX

Explanations

programming-related annotations or comments 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 @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

vie

-0.17

/***/

-0.17

 secular

-0.16

 McCart

-0.15

esteem

-0.15

nul

-0.15

]("

-0.15

_FILENO

-0.15

ulerAngles

-0.15

APPED

-0.15

POSITIVE LOGITS

var

0.25

var

0.23

 internal

0.17

ics

0.16

asti

0.16

ICS

0.15

kin

0.15

 procedural

0.15

utches

0.14

tor

0.14

Activations Density 0.003%

programming-related annotations or comments in code

No Comments

No Known Activations