INDEX

Explanations

terms related to variability and changes in conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

castle

-0.17

play

-0.17

edly

-0.16

elson

-0.16

ÃŃf

-0.15

plorer

-0.15

/place

-0.15

pel

-0.15

ificial

-0.14

lichkeit

-0.14

POSITIVE LOGITS

chart

0.19

uation

0.18

uating

0.18

(Fl

0.17

orian

0.17

ulence

0.16

shares

0.16

onium

0.16

.Fl

0.16

ugh

0.15

Activations Density 0.052%

terms related to variability and changes in conditions

No Comments

No Known Activations