INDEX

Explanations

mentions of tragic events and violence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

pud

-0.17

gy

-0.15

odzi

-0.14

ashtra

-0.14

_hid

-0.13

LEC

-0.13

à¹ģà¸ŀà¸£

-0.13

macros

-0.13

igar

-0.13

ysz

-0.13

POSITIVE LOGITS

 Palestinians

0.26

 Palestinian

0.26

 village

0.25

 olive

0.24

 Israeli

0.24

 villagers

0.23

 pale

0.23

Pale

0.23

 Village

0.20

 Bethlehem

0.20

Activations Density 0.006%

mentions of tragic events and violence

No Comments

No Known Activations