INDEX

Explanations

references to locations and structures of significance or interest

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 elsewhere

-0.15

odial

-0.15

NI

-0.14

 quanh

-0.14

nearest

-0.14

zv

-0.14

itus

-0.13

_scheme

-0.13

 hinter

-0.13

POSITIVE LOGITS

per

0.38

 high

0.31

 nest

0.25

 prec

0.22

nest

0.21

 Nest

0.21

 rising

0.21

é«ĺ

0.20

 crow

0.20

 perch

0.20

Activations Density 0.219%

references to locations and structures of significance or interest

No Comments

No Known Activations