INDEX

Explanations

mentions of Israel and its military actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bury

-0.17

antu

-0.16

ogle

-0.16

utsche

-0.15

.TR

-0.15

ìĦľëĬĶ

-0.15

chten

-0.15

Ø¨Ø§ÙĦ

-0.15

ansom

-0.15

.jet

-0.14

POSITIVE LOGITS

0.17

å¡

0.16

hone

0.15

AVED

0.14

ancel

0.14

itet

0.14

/lang

0.13

LD

0.13

 Shank

0.13

 Solic

0.13

Activations Density 0.012%

mentions of Israel and its military actions

No Comments

No Known Activations