INDEX

Explanations

discourse related to hate speech and discrimination against marginalized groups

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

reon

-0.17

 Physiology

-0.16

ÑĢÑĥÐ±

-0.16

oro

-0.15

 Ð²Ð¾Ð·ÑĢÐ°ÑģÑĤ

-0.14

idlo

-0.14

ialis

-0.14

ideshow

-0.14

izona

-0.14

ints

-0.14

POSITIVE LOGITS

Jer

0.16

å¼¹

0.15

_PD

0.14

pop

0.14

 nackte

0.14

 McMahon

0.14

.Microsoft

0.14

å¯º

0.14

ovich

0.13

æ²¢

0.13

Activations Density 0.088%

discourse related to hate speech and discrimination against marginalized groups

No Comments

No Known Activations