INDEX

Explanations

phrases that express comparisons or similes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

iman

-0.17

utsch

-0.16

æĤł

-0.16

iola

-0.16

pev

-0.15

_compiler

-0.15

IBC

-0.14

nad

-0.14

enberg

-0.14

baugh

-0.14

POSITIVE LOGITS

 clock

0.20

 nobody

0.17

 never

0.17

_True

0.16

 Nobody

0.16

 champ

0.15

usu

0.15

 normal

0.15

disposing

0.14

 champs

0.14

Activations Density 0.069%

phrases that express comparisons or similes

No Comments

No Known Activations