INDEX

Explanations

references to specific species and scientific nomenclature

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

pam

-0.15

uss

-0.15

.circular

-0.15

upal

-0.15

ambia

-0.14

 coarse

-0.14

tic

-0.14

ãĤĤãĤĬ

-0.14

:///

-0.14

POSITIVE LOGITS

(C

0.17

=C

0.16

ISR

0.16

aign

0.15

rese

0.15

(Common

0.15

 BaÄŁ

0.14

 getchar

0.14

ngr

0.14

.BorderFactory

0.14

Activations Density 0.418%

references to specific species and scientific nomenclature

No Comments

No Known Activations