INDEX

Explanations

significant numerical values related to measurement or evaluation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 Portsmouth

-0.16

orida

-0.15

/plugin

-0.15

col

-0.15

aternity

-0.15

 Everton

-0.14

Col

-0.14

Ø²Ø§

-0.14

 Winchester

-0.14

_mob

-0.13

POSITIVE LOGITS

 Rent

0.31

Rent

0.26

 Angel

0.26

 AIDS

0.25

HIV

0.25

 Larson

0.25

 rent

0.25

 Benny

0.23

 Jonathan

0.23

Angel

0.22

Activations Density 0.005%

significant numerical values related to measurement or evaluation

No Comments

No Known Activations