INDEX

Explanations

references to images and photos

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

onga

-0.19

.matches

-0.16

velle

-0.15

ver

-0.15

å¨

-0.14

ingham

-0.14

 Trem

-0.14

ilet

-0.14

ollow

-0.13

water

-0.13

POSITIVE LOGITS

arent

0.17

prak

0.17

arak

0.16

ElementType

0.14

icas

0.14

çļĦæĥħ

0.14

inati

0.14

seys

0.14

uiltin

0.14

Activations Density 0.024%

references to images and photos

No Comments

No Known Activations