INDEX

Explanations

specific terms related to systems and technology, particularly in contexts of physical systems and coded references

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

obar

-0.17

 Sponsor

-0.16

ondheim

-0.16

ä¸ĺ

-0.15

lege

-0.15

orno

-0.14

Wor

-0.14

Ð´ÐµÑĢ

-0.14

ê°Ħ

-0.14

mam

-0.14

POSITIVE LOGITS

bove

0.15

ohana

0.14

ewe

0.13

 Denn

0.13

æĩ

0.13

 forth

0.13

 embarrassing

0.13

Activations Density 0.004%

specific terms related to systems and technology, particularly in contexts of physical systems and coded references

No Comments

No Known Activations