INDEX

Explanations

references to geographical locations, particularly those including "Saint."

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

ayne

-0.16

rites

-0.15

usty

-0.15

buie

-0.14

rios

-0.14

nov

-0.14

unm

-0.14

IRT

-0.14

IVA

-0.13

erus

-0.13

POSITIVE LOGITS

 Honor

0.18

 Gilles

0.18

Urb

0.18

 Hipp

0.17

 Denis

0.17

 Saturn

0.17

 Merry

0.17

 Quentin

0.17

 Andrews

0.17

znik

0.17

Activations Density 0.029%

references to geographical locations, particularly those including "Saint."

No Comments

No Known Activations