INDEX

Explanations

references to events or situations involving loss of life or disaster

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

-slot

-0.14

ichtig

-0.14

iddy

-0.14

 ëĭ¹ìĭľ

-0.13

 Singleton

-0.13

 postcode

-0.13

 ê·¸ëŁ°

-0.13

yk

-0.13

ubat

-0.13

'ai

-0.13

POSITIVE LOGITS

 VIDEO

0.16

ilon

0.15

Portal

0.15

portal

0.15

.rf

0.15

 Lamb

0.15

#{@

0.14

 without

0.14

 towards

0.14

Activations Density 0.073%

references to events or situations involving loss of life or disaster

No Comments

No Known Activations