INDEX

Explanations

references to software testing frameworks and related constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

PERTY

-0.19

CREEN

-0.18

VOKE

-0.17

ultureInfo

-0.16

prite

-0.16

SqlParameter

-0.16

itmap

-0.16

EUR

-0.16

ymbol

-0.16

inary

-0.15

POSITIVE LOGITS

er

0.22

0.21

an

0.20

ueue

0.17

emplate

0.17

in

0.17

OMP

0.16

Activations Density 0.030%

references to software testing frameworks and related constructs

No Comments

No Known Activations