INDEX

Explanations

technical specifications or identifiers related to code and data systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

strand

-0.17

 strand

-0.16

le

-0.16

uest

-0.15

 Dise

-0.14

Vars

-0.14

 Cameron

-0.13

if

-0.13

nal

-0.13

ies

-0.13

POSITIVE LOGITS

itmap

0.18

lique

0.17

.Experimental

0.17

alic

0.15

ikk

0.14

owell

0.14

htdocs

0.14

clave

0.14

.writeValue

0.14

ObjectType

0.14

Activations Density 0.052%

technical specifications or identifiers related to code and data systems

No Comments

No Known Activations