INDEX

Explanations

instances of discovery or finding notable information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

uci

-0.18

ofil

-0.17

£

-0.16

opal

-0.15

Probe

-0.14

immel

-0.14

urette

-0.14

Visitor

-0.14

ÑĢÑĥ

-0.14

arov

-0.14

POSITIVE LOGITS

ç´¹

0.16

ë³µ

0.15

ResourceManager

0.15

ãģ°ãģĭãĤĬ

0.15

 Swords

0.15

è¦§

0.14

irut

0.14

svp

0.14

skirts

0.14

 UIStoryboard

0.14

Activations Density 0.081%

instances of discovery or finding notable information

No Comments

No Known Activations