INDEX

Explanations

references to linear equations and models

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

iw

-0.16

.tcp

-0.15

ige

-0.14

iber

-0.14

 Darkness

-0.14

ib

-0.14

.cbo

-0.14

oles

-0.14

POSITIVE LOGITS

 èĩªåĬ¨çĶŁæĪĲ

0.16

ENCH

0.15

oÅ¾

0.15

lea

0.15

ichier

0.15

 Bilg

0.15

imple

0.15

-linear

0.14

ovel

0.14

ized

0.14

Activations Density 0.023%

references to linear equations and models

No Comments

No Known Activations