INDEX

Explanations

articles indicating specificity or importance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 ever

-0.17

Î´Î®

-0.16

apter

-0.15

 Schro

-0.14

bes

-0.14

ures

-0.14

 EVER

-0.14

ropolis

-0.14

ipro

-0.14

ever

-0.14

POSITIVE LOGITS

èĪĮ

0.15

DSL

0.14

 gene

0.14

hem

0.14

dyby

0.14

iali

0.14

éı¡

0.14

ĩ´

0.13

adows

0.13

 Composite

0.13

Activations Density 0.350%

articles indicating specificity or importance

No Comments

No Known Activations