INDEX

Explanations

phrases indicating capability or ability

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ibar

-0.15

coop

-0.15

oyal

-0.14

radu

-0.13

iland

-0.13

zet

-0.13

ostel

-0.13

arias

-0.13

POSITIVE LOGITS

variant

0.16

 Outlet

0.15

rub

0.15

CACHE

0.14

 Minority

0.13

bre

0.13

.dart

0.13

ÙĲÙĨ

0.13

ensively

0.13

_opts

0.13

Activations Density 0.240%

phrases indicating capability or ability

No Comments

No Known Activations