INDEX

Explanations

the word "schemas."

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

ond

-0.20

vise

-0.17

ury

-0.16

nun

-0.15

ht

-0.15

-0.14

ppy

-0.14

 Kinder

-0.14

owler

-0.14

onda

-0.14

POSITIVE LOGITS

ToPoint

0.16

adget

0.15

_inode

0.15

CAF

0.15

 Guinness

0.15

ForRow

0.15

okud

0.15

æĽ

0.14

ieved

0.14

weet

0.14

Activations Density 0.000%

the word "schemas."

No Comments

No Known Activations