INDEX

Explanations

references to events that have concluded or are anticipated to conclude

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

beck

-0.15

COND

-0.15

akra

-0.15

enco

-0.15

coon

-0.14

ufac

-0.14

æ¹

-0.14

ÑĢÐµÑĪ

-0.14

 Nach

-0.14

ernals

-0.14

POSITIVE LOGITS

 stead

0.15

 Pole

0.15

ellen

0.15

 habit

0.15

 next

0.14

bib

0.14

-transitional

0.14

/Internal

0.14

elib

0.14

 Habit

0.14

Activations Density 0.086%

references to events that have concluded or are anticipated to conclude

No Comments

No Known Activations