INDEX

Explanations

terms related to various forms of oppression and injustice

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ØªÙĪÙĨ

-0.16

 opposition

-0.16

olina

-0.15

ldr

-0.15

Animations

-0.14

 opposite

-0.14

 Opposition

-0.14

$MESS

-0.14

ually

-0.14

agr

-0.14

POSITIVE LOGITS

zech

0.15

incident

0.14

 incidental

0.14

WB

0.14

don

0.14

 incident

0.14

ÂŃs

0.13

aug

0.13

UGIN

0.13

Activations Density 0.014%

terms related to various forms of oppression and injustice

No Comments

No Known Activations