INDEX

Explanations

references to measurements, quantities, and interactions among various elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

 circ

-0.16

atron

-0.15

BC

-0.14

agens

-0.14

á»ģn

-0.14

itler

-0.14

inha

-0.14

 Jack

-0.14

Ã©m

-0.13

ied

-0.13

POSITIVE LOGITS

0.18

 minut

0.15

czy

0.15

ãģĿãģĨãģª

0.15

ÃĹ↵↵

0.15

 Minute

0.15

ritz

0.14

ritt

0.14

radan

0.14

Ĭ¶

0.14

Activations Density 0.205%

references to measurements, quantities, and interactions among various elements

No Comments

No Known Activations