INDEX

Explanations

references to specific locations or entities marked by the letter 'H'

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

anken

-0.17

isse

-0.16

chor

-0.15

ost

-0.15

uffman

-0.15

osta

-0.15

-0.14

 Gard

-0.14

abilit

-0.14

isser

-0.14

POSITIVE LOGITS

erts

0.24

engo

0.24

ert

0.23

umber

0.20

udder

0.18

oun

0.17

agger

0.17

MP

0.16

amp

0.16

udd

0.16

Activations Density 0.012%

references to specific locations or entities marked by the letter 'H'

No Comments

No Known Activations