INDEX

Explanations

instances of the abbreviation "Sp," likely indicating a specific name or term associated with significant topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ÑıÐ±

-0.16

venes

-0.16

 MetroFramework

-0.15

hq

-0.15

veis

-0.15

erais

-0.15

 ../../../

-0.14

ancock

-0.14

erase

-0.14

eras

-0.14

POSITIVE LOGITS

Sp

0.22

otted

0.18

sp

0.18

ree

0.18

bau

0.17

Sp

0.17

-sp

0.16

emann

0.16

loid

0.16

iro

0.16

Activations Density 0.031%

instances of the abbreviation "Sp," likely indicating a specific name or term associated with significant topics

No Comments

No Known Activations