INDEX

Explanations

technical terms and symbols commonly used in programming and data analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ä»ĺãģį

-0.15

ieur

-0.15

 slow

-0.14

ean

-0.14

uÃ©

-0.14

 pract

-0.14

angelo

-0.13

ģn

-0.13

 upset

-0.13

aneous

-0.13

POSITIVE LOGITS

 xlink

0.15

á»ģn

0.15

-transition

0.14

uitka

0.14

Speaker

0.14

 Swim

0.14

-toast

0.14

rys

0.14

OLA

0.14

_relations

0.14

Activations Density 0.030%

technical terms and symbols commonly used in programming and data analysis

No Comments

No Known Activations