INDEX

Explanations

date references within the text

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

åĢĴ

-0.17

dit

-0.17

inp

-0.15

emaker

-0.14

piel

-0.14

fully

-0.14

arte

-0.14

 analogy

-0.14

rias

-0.14

 deed

-0.13

POSITIVE LOGITS

åª

0.16

referrer

0.16

lund

0.15

 Rein

0.15

PROP

0.14

engkap

0.14

wards

0.14

ernet

0.14

lish

0.14

Activations Density 0.017%

date references within the text

No Comments

No Known Activations