INDEX

Explanations

references to the letter "K" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

annes

-0.18

uger

-0.16

ahn

-0.16

NIL

-0.16

af

-0.16

uges

-0.15

bject

-0.15

wid

-0.15

ardash

-0.15

argas

-0.14

POSITIVE LOGITS

haled

0.24

ieran

0.22

eri

0.20

ately

0.19

acey

0.19

rys

0.19

sen

0.19

irst

0.18

jet

0.17

ofi

0.16

Activations Density 0.024%

references to the letter "K" in various contexts

No Comments

No Known Activations