INDEX

Explanations

references to various roles, functions, or organizational elements related to systems and control structures

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

-addons

-0.17

gili

-0.15

à¸´à¹Ģà¸¨à¸©

-0.15

gow

-0.15

bourg

-0.15

 Sadd

-0.14

ambi

-0.14

 Platforms

-0.14

ichern

-0.14

Borders

-0.14

POSITIVE LOGITS

 control

0.19

err

0.16

 controls

0.15

ctl

0.15

ä¼į

0.15

-controlled

0.15

_ctl

0.15

orbit

0.14

æİ§åĪ¶

0.14

Activations Density 0.065%

references to various roles, functions, or organizational elements related to systems and control structures

No Comments

No Known Activations