INDEX

Explanations

expressions of gratitude and thankfulness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

lassen

-0.17

engan

-0.17

usch

-0.15

 sadly

-0.14

orro

-0.14

vault

-0.14

 itself

-0.14

obo

-0.14

_PAD

-0.13

POSITIVE LOGITS

ipt

0.15

enia

0.14

Ø§ØªØ±

0.14

GuidId

0.14

kaz

0.14

á»ĵi

0.14

htar

0.13

ê¸°ë¡ľ

0.13

OSC

0.13

_Statics

0.13

Activations Density 0.027%

expressions of gratitude and thankfulness

No Comments

No Known Activations