INDEX

Explanations

programming-related terms and code structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

agan

-0.17

ieur

-0.16

agar

-0.15

ivi

-0.14

aga

-0.14

atan

-0.13

¬¬

-0.13

ui

-0.13

ard

-0.13

POSITIVE LOGITS

ĶåĽŀ

0.15

ï»¿using

0.14

_unpack

0.14

 acomp

0.14

 putas

0.14

loor

0.14

Lau

0.14

Æ¯

0.14

 Ð»Ð°Ðº

0.14

actionDate

0.14

Activations Density 0.068%

programming-related terms and code structure

No Comments

No Known Activations