INDEX

Explanations

mathematical notations related to constants and variables

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ab

-0.15

sel

-0.15

 Wagner

-0.15

lf

-0.14

ron

-0.13

 carbon

-0.13

Ìģt

-0.13

 Grim

-0.13

å¹³

-0.13

ÑıÐ²

-0.13

POSITIVE LOGITS

ģm

0.15

 Mile

0.15

ipzig

0.15

ANNOT

0.15

Ð°Ð»Ð¾Ð²

0.14

æľĭ

0.14

ogne

0.14

UserCode

0.14

 initWithStyle

0.14

ryn

0.14

Activations Density 0.131%

mathematical notations related to constants and variables

No Comments

No Known Activations