INDEX

Explanations

numerical data or values associated with statistical analysis

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

quate

-0.16

arda

-0.15

reau

-0.15

andler

-0.14

peare

-0.14

uet

-0.14

berapa

-0.14

ometr

-0.14

zcze

-0.14

utz

-0.13

POSITIVE LOGITS

rou

0.19

reen

0.15

ifax

0.14

 Linden

0.14

-alist

0.14

Wis

0.14

á»©

0.14

cheng

0.14

ewhat

0.14

Erf

0.13

Activations Density 0.048%

numerical data or values associated with statistical analysis

No Comments

No Known Activations