INDEX

Explanations

specialized technical terms and nomenclature related to coding and 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 @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

rio

-0.16

 match

-0.15

 Rican

-0.14

ÑĨÐ¸Ð½

-0.14

 Gone

-0.14

ONTAL

-0.14

uchos

-0.14

oren

-0.13

beer

-0.13

Ð¾Ð»Ð¾

-0.13

POSITIVE LOGITS

 which

0.20

ÂĿ

0.19

which

0.18

assi

0.16

gamber

0.15

erta

0.15

etta

0.15

à¤Łà¤°

0.15

å§Ĩ

0.15

aliyet

0.15

Activations Density 0.300%

specialized technical terms and nomenclature related to coding and software development

No Comments

No Known Activations