INDEX

Explanations

commands or directives that draw attention

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

uner

-0.18

eka

-0.17

ioned

-0.16

ãĥķãĥĪ

-0.16

ê³

-0.15

ropolis

-0.15

ivirus

-0.15

cott

-0.15

ÐµÐ³Ð¾ÑĢ

-0.15

POSITIVE LOGITS

 closely

0.25

no

0.22

 look

0.19

 familiar

0.18

Fam

0.18

how

0.18

 Look

0.17

ma

0.17

 Sharp

0.17

 LOOK

0.17

Activations Density 0.014%

commands or directives that draw attention

No Comments

No Known Activations