INDEX

Explanations

terms and phrases indicating presence or existence on a web page

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

pu

-0.15

hue

-0.15

umbled

-0.15

ahy

-0.14

ulas

-0.14

_TA

-0.14

istÃ©

-0.14

istes

-0.14

nap

-0.13

kul

-0.13

POSITIVE LOGITS

Mil

0.15

|_|

0.15

Emitter

0.14

arket

0.14

äºĭæĥħ

0.14

ylon

0.14

 char

0.13

Mt

0.13

endent

0.13

ou

0.13

Activations Density 0.003%

terms and phrases indicating presence or existence on a web page

No Comments

No Known Activations