INDEX

Explanations

code-related terminology and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

adores

-0.15

 bulk

-0.15

 Bulk

-0.15

ilent

-0.15

ook

-0.14

pell

-0.14

ims

-0.14

ãĥģãĥ¥

-0.14

yna

-0.14

iolet

-0.14

POSITIVE LOGITS

 void

0.17

ignet

0.17

exports

0.17

 ((((

0.16

CallCheck

0.15

ium

0.15

_typeof

0.15

_IMPORTED

0.15

$__

0.15

ï»¿#

0.15

Activations Density 0.250%

code-related terminology and structures

No Comments

No Known Activations