INDEX

Explanations

names of individuals, particularly those involved in various articles or discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

á»£

-0.15

 tslint

-0.15

angan

-0.15

Ã¨o

-0.14

awi

-0.14

oga

-0.14

ictory

-0.14

ÐµÑĢÐ°Ð¿

-0.13

Æ°á»£

-0.13

ongan

-0.13

POSITIVE LOGITS

 arter

0.15

.Interop

0.14

/GPL

0.14

_MT

0.13

 sire

0.13

 oven

0.13

ÛĮÙĨÚ©

0.13

registry

0.13

elsing

0.13

 rapid

0.12

Activations Density 0.010%

names of individuals, particularly those involved in various articles or discussions

No Comments

No Known Activations