INDEX

Explanations

code-related elements and syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 ↵↵

-0.18

 Bing

-0.15

ãĥ«ãĥī

-0.14

ceil

-0.14

@qq

-0.14

 Newtown

-0.14

Et

-0.14

xlsx

-0.14

imap

-0.13

 lith

-0.13

POSITIVE LOGITS

Parms

0.23

 thunk

0.18

undry

0.16

bed

0.16

 Hashtable

0.16

parms

0.15

.nlm

0.15

ListOf

0.15

.elementAt

0.15

 queryInterface

0.14

Activations Density 0.616%

code-related elements and syntax

No Comments

No Known Activations