INDEX

Explanations

references to destruction or significant damage

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

ç«ĭãģ¡

-0.16

eza

-0.16

ÄĽ

-0.15

nez

-0.15

cala

-0.15

boro

-0.15

ãĥ³ãĥĳ

-0.14

 boxed

-0.14

annon

-0.14

pu

-0.14

POSITIVE LOGITS

 apart

0.38

 Apart

0.29

 torn

0.27

 tearing

0.26

 tore

0.26

 Tear

0.25

 tear

0.25

rip

0.23

 ripped

0.23

 ripping

0.22

Activations Density 0.017%

references to destruction or significant damage

No Comments

No Known Activations