INDEX

Explanations

themes related to online harassment and personal attacks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

alk

-0.15

flex

-0.15

rik

-0.15

Backing

-0.14

rire

-0.14

ezi

-0.14

hiba

-0.14

etus

-0.14

anter

-0.14

onen

-0.14

POSITIVE LOGITS

 majority

0.17

 Majority

0.15

 toxicity

0.15

hq

0.15

 myself

0.14

 Ð²Ð½ÑĥÑĤÑĢÐ¸

0.14

.scalablytyped

0.14

 majÄħ

0.14

whelming

0.13

 veteran

0.13

Activations Density 0.009%

themes related to online harassment and personal attacks

No Comments

No Known Activations