INDEX

Explanations

instances of the word "beyond."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

uisse

-0.17

ulings

-0.16

ialis

-0.16

bbe

-0.15

ILED

-0.15

ucch

-0.14

hlas

-0.14

 thÃªm

-0.14

 SearchResult

-0.14

åĪ°çļĦ

-0.14

POSITIVE LOGITS

 mere

0.29

words

0.25

 merely

0.25

 borders

0.23

 simply

0.23

 Compare

0.23

 repro

0.23

 beyond

0.22

 Beyond

0.22

 bounds

0.22

Activations Density 0.034%

instances of the word "beyond."

No Comments

No Known Activations