INDEX

Explanations

references to mobs and mob-related activities or concepts

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

istrovstvÃŃ

-0.18

umm

-0.16

uppe

-0.15

icl

-0.15

umer

-0.15

labs

-0.15

iffe

-0.14

 Rowe

-0.14

iá»ĩu

-0.14

ICA

-0.14

POSITIVE LOGITS

by

0.15

fold

0.15

rana

0.14

Ta

0.14

has

0.14

Lev

0.14

QUIRE

0.14

Af

0.14

 Jack

0.14

ards

0.13

Activations Density 0.010%

references to mobs and mob-related activities or concepts

No Comments

No Known Activations