INDEX

Explanations

references to the action of zooming in and out in various contexts

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

hek

-0.19

ÙĤØ§ÙĦ

-0.15

 âĹĦ

-0.15

PHA

-0.15

ibox

-0.14

aby

-0.14

imonial

-0.13

iphone

-0.13

reak

-0.13

rea

-0.13

POSITIVE LOGITS

ers

0.15

eroon

0.15

iswa

0.14

_spaces

0.14

heets

0.14

esium

0.14

erif

0.14

Unused

0.13

lac

0.13

-tip

0.13

Activations Density 0.005%

references to the action of zooming in and out in various contexts

No Comments

No Known Activations