INDEX

Explanations

mentions of the term "alg."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ring

-0.21

rand

-0.20

LC

-0.19

oon

-0.19

rw

-0.18

rant

-0.18

rs

-0.18

uir

-0.18

ran

-0.18

rana

-0.18

POSITIVE LOGITS

undy

0.18

lish

0.18

rieved

0.18

ularity

0.17

rove

0.17

ieri

0.16

redients

0.16

anik

0.16

lasses

0.16

ards

0.16

Activations Density 0.043%

mentions of the term "alg."

No Comments

No Known Activations