INDEX

Explanations

references to programming languages and their components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

bjerg

-0.18

shaw

-0.16

ptest

-0.15

IBC

-0.14

ofire

-0.14

ittel

-0.14

emoc

-0.14

loha

-0.14

rez

-0.14

vla

-0.14

POSITIVE LOGITS

arness

0.15

½æķ°

0.14

teg

0.13

à¤¸à¤°

0.13

æ³£

0.13

omin

0.13

 pang

0.12

ollar

0.12

inct

0.12

(("

0.12

Activations Density 1.424%

references to programming languages and their components

No Comments

No Known Activations