INDEX

Explanations

expressions of significant scale or impact

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

oon

-0.15

Î¯Î¸

-0.14

avi

-0.14

och

-0.14

tol

-0.14

ãģ¡ãĤĥ

-0.14

shelf

-0.14

/rs

-0.14

stant

-0.14

POSITIVE LOGITS

ÑĢÐ³

0.15

contri

0.15

Lag

0.15

ê³µ

0.14

ë¡Ģ

0.14

istributor

0.13

.ie

0.13

iny

0.13

 Blasio

0.13

IE

0.13

Activations Density 0.001%

expressions of significant scale or impact

No Comments

No Known Activations