INDEX

Explanations

phrases related to visual presentation and showing information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ha

-0.16

fid

-0.15

itter

-0.15

Sez

-0.15

xon

-0.15

haul

-0.14

Esp

-0.14

issan

-0.14

ona

-0.14

ched

-0.14

POSITIVE LOGITS

etten

0.15

roe

0.15

ythe

0.14

iÄįka

0.14

edl

0.14

ETO

0.14

-nil

0.14

Selective

0.13

ients

0.13

anlÄ±

0.13

Activations Density 0.056%

phrases related to visual presentation and showing information

No Comments

No Known Activations