INDEX

Explanations

the presence of terms related to functionality and support within technical or operational contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

 Inflate

-0.15

ael

-0.15

aliases

-0.14

 comb

-0.14

ali

-0.14

 alias

-0.14

 à¤ªà¤¡

-0.14

 Carroll

-0.14

ADO

-0.13

rav

-0.13

POSITIVE LOGITS

ukan

0.15

appable

0.15

erre

0.14

 Ment

0.14

uky

0.14

 Ð±Ð»

0.14

ë²Į

0.14

tain

0.14

ollar

0.14

claimer

0.14

Activations Density 0.022%

the presence of terms related to functionality and support within technical or operational contexts

No Comments

No Known Activations