INDEX

Explanations

references to definitions and theoretical concepts in a mathematical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

Ø±ÙĬØ¨

-0.15

pto

-0.14

 Schultz

-0.14

thro

-0.14

Ð¼Ñĭ

-0.13

legen

-0.13

vice

-0.13

legt

-0.13

amped

-0.13

tru

-0.13

POSITIVE LOGITS

atsapp

0.14

orado

0.14

Ľå»º

0.14

alah

0.14

ħn

0.14

 blink

0.13

ceae

0.13

 Ø§Ø±Ø¯

0.13

hardt

0.13

 texts

0.13

Activations Density 0.010%

references to definitions and theoretical concepts in a mathematical context

No Comments

No Known Activations