INDEX

Explanations

references to dates or specific time identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ted

-0.18

led

-0.17

LED

-0.17

oine

-0.15

rias

-0.15

orious

-0.15

eel

-0.15

annes

-0.14

lant

-0.14

POSITIVE LOGITS

roe

0.23

astery

0.22

ochrome

0.20

itored

0.20

ero

0.19

soon

0.19

mon

0.18

sters

0.18

(mon

0.18

trÃ©al

0.17

Activations Density 0.016%

references to dates or specific time identifiers

No Comments

No Known Activations