INDEX

Explanations

statistics and rankings associated with various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

¿ł

-0.17

íļį

-0.16

ãģ°ãģĭãĤĬ

-0.15

ctal

-0.15

trand

-0.14

Î¬Î»

-0.14

ë§¤

-0.14

orderby

-0.14

amu

-0.14

hetto

-0.14

POSITIVE LOGITS

 followed

0.28

follow

0.19

 closely

0.18

 plurality

0.16

AbsolutePath

0.16

tie

0.16

aint

0.16

 ahead

0.15

ikki

0.15

far

0.15

Activations Density 0.084%

statistics and rankings associated with various subjects

No Comments

No Known Activations