INDEX

Explanations

phrases or terms related to mathematical or scientific points and measurements

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

aby

-0.16

raith

-0.15

Ã¡n

-0.15

adro

-0.15

riel

-0.15

kiem

-0.15

éĩı

-0.15

kir

-0.14

ãĥ¼ãĤ¯

-0.14

illy

-0.14

POSITIVE LOGITS

/moment

0.15

 SOUR

0.14

rosso

0.14

Ð°ÑĢÐ°Ð¼

0.14

 adulte

0.14

á»ı

0.14

rippling

0.14

 addChild

0.13

ivel

0.13

insula

0.13

Activations Density 0.054%

phrases or terms related to mathematical or scientific points and measurements

No Comments

No Known Activations