INDEX

Explanations

references to permanent and temporary statuses or conditions

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

fully

-0.15

_COMPAT

-0.15

fulness

-0.15

onne

-0.14

 ÏĥÏħÎ¼ÏĢ

-0.14

hoot

-0.14

Descriptors

-0.13

pector

-0.13

Ð²ÐµÐ´

-0.13

heritance

-0.13

POSITIVE LOGITS

/per

0.29

 fixture

0.29

 fixtures

0.29

/temp

0.27

 solution

0.26

 residents

0.25

 resident

0.25

 solutions

0.24

 residence

0.24

 fixes

0.23

Activations Density 0.040%

references to permanent and temporary statuses or conditions

No Comments

No Known Activations