INDEX

Explanations

references to scientific theories and their associated data or analysis

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

 Experimental

-0.16

nev

-0.16

 experimental

-0.16

lander

-0.16

Experimental

-0.16

Dlg

-0.15

itore

-0.15

ales

-0.15

 territorial

-0.14

edula

-0.14

POSITIVE LOGITS

 Astroph

0.20

ast

0.20

 Subaru

0.20

fid

0.19

 stars

0.19

 Kenn

0.18

 discre

0.17

OGLE

0.17

/catalog

0.17

 Stars

0.17

Activations Density 0.029%

references to scientific theories and their associated data or analysis

No Comments

No Known Activations