INDEX

Explanations

expressions of loyalty and friendship

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ì¦Ŀ

-0.18

omore

-0.14

Ð¾Ð»Ð¾Ð¼

-0.14

isku

-0.14

yay

-0.14

ersist

-0.13

vic

-0.13

iks

-0.13

rani

-0.13

oh

-0.13

POSITIVE LOGITS

 indeed

0.26

 Indeed

0.19

itable

0.19

Indeed

0.18

LOT

0.17

lot

0.16

 quite

0.16

Lot

0.15

 pretty

0.15

 alot

0.15

Activations Density 0.172%

expressions of loyalty and friendship

No Comments

No Known Activations