INDEX

Explanations

numerical values or statistics related to events or occurrences

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

iss

-0.15

mina

-0.15

ugen

-0.15

uc

-0.15

ppe

-0.15

-regexp

-0.15

 Triangle

-0.14

roid

-0.14

 subt

-0.13

Py

-0.13

POSITIVE LOGITS

ÑģÐ¾Ð½

0.15

è

0.15

Ð°ÑĩÐµ

0.15

Ø²Ø©

0.14

-Ta

0.14

athi

0.13

éĻĲ

0.13

eren

0.13

ansa

0.13

é«ĺéĢŁ

0.13

Activations Density 0.024%

numerical values or statistics related to events or occurrences

No Comments

No Known Activations