INDEX

Explanations

references to individuals and groups involved in a variety of roles, particularly in a professional or community context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

arching

-0.15

ycz

-0.15

icc

-0.15

_marshall

-0.14

oulos

-0.13

LOPT

-0.13

Ð¾ÑĤÐ¾ÑĢ

-0.13

atica

-0.13

uhe

-0.13

kie

-0.13

POSITIVE LOGITS

 Lilly

0.15

ABS

0.15

rote

0.14

ÏĩÎ¿

0.14

 frequent

0.14

ëĮĢíĳľ

0.14

ignon

0.14

æŀĿ

0.14

ickets

0.14

è¦

0.14

Activations Density 0.074%

references to individuals and groups involved in a variety of roles, particularly in a professional or community context

No Comments

No Known Activations