INDEX

Explanations

references to seasons and dimensions associated with various series or materials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

-0.17

ogra

-0.16

exus

-0.15

alink

-0.15

onis

-0.15

UNET

-0.15

-0.14

POSITIVE LOGITS

0.17

ì°©

0.14

enna

0.14

trinsic

0.13

-origin

0.13

Ā

0.13

atik

0.13

æĲ

0.13

ther

0.12

Activations Density 0.131%

references to seasons and dimensions associated with various series or materials

No Comments

No Known Activations