INDEX

Explanations

elements of press releases

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

ije

-0.15

ance

-0.15

ivor

-0.14

oon

-0.14

itage

-0.14

oyal

-0.14

entin

-0.14

wer

-0.14

ism

-0.14

let

-0.13

POSITIVE LOGITS

 PRESS

0.22

PRESS

0.17

 today

0.17

press

0.17

ilies

0.16

Press

0.15

 Press

0.15

 Posted

0.15

(PR

0.15

 NEWS

0.15

Activations Density 0.044%

elements of press releases

No Comments

No Known Activations