INDEX

Explanations

references to quality or adequacy, often in relation to performance or attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ars

-0.17

iche

-0.15

-0.14

à¤Ĥà¤ľ

-0.14

san

-0.14

MBOL

-0.14

ëŁ

-0.14

ÃĶNG

-0.14

ott

-0.14

 Lars

-0.13

POSITIVE LOGITS

-sized

0.20

 sized

0.19

erif

0.17

erre

0.16

ately

0.16

ably

0.16

leme

0.15

isy

0.15

íŀĪ

0.15

urnal

0.15

Activations Density 0.009%

references to quality or adequacy, often in relation to performance or attributes

No Comments

No Known Activations