INDEX

Explanations

content related to nature, events, and personal reflections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

-0.15

İ

-0.14

esco

-0.14

 Emer

-0.14

 around

-0.14

ylum

-0.13

opoly

-0.13

Å¡ak

-0.13

ICAST

-0.13

 Goth

-0.13

POSITIVE LOGITS

fed

0.15

ptune

0.14

è®¿

0.14

 CreateTable

0.13

allery

0.13

ogui

0.13

 FLAGS

0.13

LATED

0.13

erras

0.12

 legisl

0.12

Activations Density 0.042%

content related to nature, events, and personal reflections

No Comments

No Known Activations