INDEX

Explanations

technical terms related to software and programming tools

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

InputLabel

-0.14

arat

-0.14

umm

-0.13

Uvs

-0.13

GBK

-0.13

istrict

-0.13

å¦ĥ

-0.13

istÃ©

-0.13

idents

-0.13

POSITIVE LOGITS

isoft

0.19

Studio

0.16

 mode

0.16

-mode

0.16

zilla

0.16

nu

0.15

ofire

0.15

 Mode

0.15

Ware

0.15

{},

0.15

Activations Density 0.335%

technical terms related to software and programming tools

No Comments

No Known Activations