INDEX

Explanations

programming keywords and concepts related to component state and behavior in software development

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ledon

-0.14

ecute

-0.14

vale

-0.14

ubern

-0.13

_VC

-0.13

ÑĬ

-0.13

 AssemblyCopyright

-0.13

ìĽĶë¶ĢíĦ°

-0.13

$self

-0.13

iners

-0.13

POSITIVE LOGITS

lyph

0.17

 anthem

0.15

rokes

0.15

eo

0.15

´Ī

0.14

egis

0.14

edback

0.14

lys

0.14

_bio

0.14

acter

0.14

Activations Density 0.048%

programming keywords and concepts related to component state and behavior in software development

No Comments

No Known Activations