INDEX

Explanations

direct speech or quotes in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ScreenState

-0.16

thon

-0.14

apan

-0.14

ibbean

-0.14

avel

-0.14

odyn

-0.14

arian

-0.14

licht

-0.14

odo

-0.14

lias

-0.14

POSITIVE LOGITS

defs

0.15

 Gord

0.14

stup

0.13

Managed

0.13

XT

0.13

entai

0.13

anzi

0.13

Ð´Ð°ÑĤ

0.12

@[

0.12

Activations Density 0.034%

direct speech or quotes in the text

No Comments

No Known Activations