INDEX

Explanations

references to Planned Parenthood

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ic

-0.17

born

-0.16

 Lazar

-0.15

ÑģÑĤÐ°Ð½Ð¾Ð²

-0.14

nar

-0.14

wald

-0.14

oun

-0.14

zen

-0.14

wner

-0.14

ashes

-0.14

POSITIVE LOGITS

rios

0.17

peg

0.15

CompleteListener

0.15

oeff

0.15

alborg

0.15

pluck

0.14

erp

0.14

YYS

0.14

phinx

0.14

reich

0.14

Activations Density 0.002%

references to Planned Parenthood

No Comments

No Known Activations