INDEX

Explanations

code syntax elements, particularly those related to markup or programming language structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

umont

-0.18

_simps

-0.16

zel

-0.16

ipers

-0.15

tur

-0.15

antro

-0.14

inton

-0.14

uting

-0.14

ieber

-0.14

anzi

-0.13

POSITIVE LOGITS

asco

0.17

abcdefghijkl

0.15

ades

0.15

ewn

0.15

uyo

0.14

çī

0.14

).__

0.14

 Innoc

0.14

.streaming

0.14

imeter

0.14

Activations Density 0.007%

code syntax elements, particularly those related to markup or programming language structures

No Comments

No Known Activations