INDEX

Explanations

occurrences of the word "ach" and related variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

lene

-0.17

elter

-0.16

enus

-0.15

 Quadr

-0.15

ackbar

-0.14

iem

-0.14

à¥ĩà¤£

-0.14

 medic

-0.14

 Stout

-0.14

fas

-0.14

POSITIVE LOGITS

amarin

0.17

erosis

0.15

rech

0.15

ãĥ³ãĥĨãĤ£

0.15

sor

0.14

ĳ

0.14

Ã¼rk

0.14

 Croat

0.14

verte

0.14

ton

0.14

Activations Density 0.015%

occurrences of the word "ach" and related variations

No Comments

No Known Activations