INDEX

Explanations

expressions related to protests and social injustice

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 kesin

-0.15

 Ð¾Ð±ÑıÐ·

-0.15

epy

-0.14

Į¨

-0.14

decltype

-0.14

pron

-0.14

 permanently

-0.14

isex

-0.14

$__

-0.13

 pron

-0.13

POSITIVE LOGITS

 harmless

0.49

 innocent

0.47

 innoc

0.47

 perfectly

0.46

 legitimate

0.46

 lawful

0.36

 benign

0.36

 Innoc

0.36

æŃ£å¸¸

0.34

 valid

0.34

Activations Density 0.560%

expressions related to protests and social injustice

No Comments

No Known Activations