INDEX

Explanations

references to images or visual media

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

olumn

-0.19

scene

-0.15

ped

-0.14

gir

-0.14

obot

-0.14

aven

-0.14

erg

-0.14

dds

-0.14

 Held

-0.14

 Spart

-0.14

POSITIVE LOGITS

ita

0.16

SizePolicy

0.16

INA

0.15

 commodo

0.15

ntl

0.14

 VÃ¡clav

0.14

ìĨĮë¥¼

0.14

0.13

indre

0.13

hound

0.13

Activations Density 0.002%

references to images or visual media

No Comments

No Known Activations