INDEX

Explanations

references to incidents of hate crimes and community support in the context of violence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

gua

-0.18

ceptive

-0.15

Ä±b

-0.15

ê°ģ

-0.15

jam

-0.14

opian

-0.14

_HC

-0.14

COLUMN

-0.14

lya

-0.14

RVA

-0.13

POSITIVE LOGITS

 prelim

0.24

 preliminary

0.24

 Prel

0.20

 initial

0.19

 motive

0.18

 investigation

0.17

 ruled

0.17

 Initial

0.17

Initial

0.16

[](

0.16

Activations Density 0.059%

references to incidents of hate crimes and community support in the context of violence

No Comments

No Known Activations