INDEX

Explanations

references to steam or steam-related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

canf

-0.16

umen

-0.15

zens

-0.14

BASH

-0.14

orp

-0.14

ipers

-0.14

uate

-0.14

lip

-0.14

epad

-0.14

 airspace

-0.14

POSITIVE LOGITS

roller

0.30

ROLLER

0.21

boat

0.21

 Powered

0.21

 locom

0.21

rollers

0.21

Powered

0.20

ier

0.19

works

0.18

-powered

0.18

Activations Density 0.012%

references to steam or steam-related concepts

No Comments

No Known Activations