INDEX

Explanations

names and references to individuals and organizations in educational or professional contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Mutable

-0.16

mez

-0.15

nze

-0.15

iverz

-0.14

ackbar

-0.14

evice

-0.14

ucci

-0.14

ensity

-0.14

ands

-0.14

alous

-0.14

POSITIVE LOGITS

phony

0.14

igor

0.14

opoulos

0.14

åĿĩ

0.14

 Chest

0.14

umper

0.14

Õ¡

0.14

ä¸ĬäºĨ

0.13

kal

0.13

Nam

0.13

Activations Density 0.116%

names and references to individuals and organizations in educational or professional contexts

No Comments

No Known Activations