INDEX

Explanations

references to various dates and publication details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

asm

-0.19

nt

-0.18

ASET

-0.15

ICA

-0.15

hir

-0.15

ime

-0.15

eno

-0.14

apt

-0.14

bie

-0.14

stm

-0.14

POSITIVE LOGITS

Â·Â·

0.24

Â·Â·Â·Â·

0.23

ó

0.21

Ð¿ÑĢÐ°Ð²

0.17

Î³Î¬

0.15

emade

0.15

ully

0.15

ovsky

0.15

Activations Density 0.012%

references to various dates and publication details

No Comments

No Known Activations