INDEX

Explanations

specific terms related to performance metrics or evaluations in various contexts

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

oproject

-0.15

ilda

-0.14

ObjectContext

-0.14

DeltaTime

-0.14

 SIMD

-0.14

_OCCURRED

-0.14

 Albert

-0.14

 Jackson

-0.14

iloc

-0.13

loven

-0.13

POSITIVE LOGITS

 Puppet

0.34

 puppet

0.29

 facts

0.22

 provider

0.22

 resource

0.21

facts

0.21

pup

0.21

/provider

0.21

.pp

0.20

provider

0.20

Activations Density 0.009%

specific terms related to performance metrics or evaluations in various contexts

No Comments

No Known Activations