INDEX

Explanations

references to educational institutions and settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 Alternative

-0.16

 ActiveForm

-0.16

.FC

-0.15

olders

-0.14

.parents

-0.14

uluk

-0.14

 Cole

-0.14

.utility

-0.14

á»ĳn

-0.13

 Arth

-0.13

POSITIVE LOGITS

/templates

0.15

¢åįķ

0.15

/js

0.14

iena

0.14

Ð¾Ð¶

0.14

Ð¼Ð¾ÑĢ

0.14

rego

0.14

girl

0.14

ica

0.13

_SLAVE

0.13

Activations Density 0.052%

references to educational institutions and settings

No Comments

No Known Activations