INDEX

Explanations

references to visual elements and their qualities 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 @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

-0.16

vice

-0.16

ish

-0.16

list

-0.15

ilet

-0.15

 Hats

-0.15

arest

-0.15

utsche

-0.15

oli

-0.15

alic

-0.15

POSITIVE LOGITS

ERTICAL

0.16

engeance

0.16

rub

0.16

 hÆ°á»Łng

0.15

omap

0.15

/print

0.15

izations

0.15

Î´Î®

0.15

aneously

0.14

ibrate

0.14

Activations Density 0.022%

references to visual elements and their qualities in the text

No Comments

No Known Activations