INDEX

Explanations

technical terms and identifiers related to network systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

riel

-0.16

acob

-0.15

ippi

-0.14

elli

-0.14

izza

-0.14

ipt

-0.13

Nem

-0.13

ivirus

-0.13

afort

-0.13

_##

-0.13

POSITIVE LOGITS

_:*

0.15

ÎºÏħ

0.15

0.14

Ros

0.13

.low

0.13

itÃł

0.13

Dy

0.13

ceptar

0.13

.DisplayName

0.13

 susp

0.13

Activations Density 0.451%

technical terms and identifiers related to network systems

No Comments

No Known Activations