INDEX

Explanations

identifiers or markers for various subjects or entities

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

ancia

-0.15

 Ká»³

-0.14

uder

-0.14

ut

-0.14

uida

-0.14

meet

-0.14

acct

-0.14

ITA

-0.14

rib

-0.13

 gover

-0.13

POSITIVE LOGITS

etsk

0.20

anos

0.17

olson

0.16

umbed

0.16

kla

0.15

oped

0.15

Thr

0.15

iley

0.15

Rum

0.14

sci

0.14

Activations Density 0.020%

identifiers or markers for various subjects or entities

No Comments

No Known Activations