INDEX

Explanations

names, particularly related to authors and their works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

spin

-0.18

awn

-0.17

richt

-0.16

íıĲ

-0.16

orna

-0.16

urge

-0.15

ersh

-0.15

-quarters

-0.15

resse

-0.15

stadt

-0.14

POSITIVE LOGITS

imeter

0.20

shire

0.19

mutations

0.18

pendicular

0.18

 capita

0.18

agon

0.18

rier

0.17

_GRANTED

0.17

 annum

0.17

iphery

0.17

Activations Density 0.054%

names, particularly related to authors and their works

No Comments

No Known Activations