INDEX

Explanations

significant keywords or phrases associated with topics in legal, financial, 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 @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

cken

-0.18

faf

-0.16

faction

-0.15

 ÎłÎ±Î½

-0.15

gow

-0.15

 pins

-0.14

.wik

-0.14

oÅĻ

-0.14

fact

-0.14

ÎłÎĳ

-0.14

POSITIVE LOGITS

Ã§

0.17

irection

0.15

inton

0.15

LabelText

0.15

 Laboratory

0.15

irling

0.15

LAB

0.14

om

0.14

jango

0.14

ench

0.14

Activations Density 0.004%

significant keywords or phrases associated with topics in legal, financial, or operational contexts

No Comments

No Known Activations