INDEX

Explanations

abbreviations for various roles and types within public relations and communication sectors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

egas

-0.18

arts

-0.18

ikes

-0.16

erval

-0.16

andler

-0.16

ihar

-0.16

ep

-0.16

ajan

-0.16

ene

-0.15

ega

-0.15

POSITIVE LOGITS

hythm

0.20

iginal

0.16

aphael

0.16

ivate

0.16

amework

0.15

erli

0.15

 Congo

0.15

PED

0.15

erer

0.15

haps

0.15

Activations Density 0.043%

abbreviations for various roles and types within public relations and communication sectors

No Comments

No Known Activations