INDEX

Explanations

specific details about roles, locations, and organizational structure within an educational 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 @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 procent

-0.16

LIK

-0.15

vez

-0.14

 Weiner

-0.13

 indeed

-0.13

 QSize

-0.13

uckets

-0.13

 yesterday

-0.12

 çĪ

-0.12

unes

-0.12

POSITIVE LOGITS

 please

0.20

 unless

0.20

 inquire

0.18

please

0.18

 Except

0.18

unless

0.18

listed

0.18

 except

0.18

 Please

0.17

Except

0.17

Activations Density 0.055%

specific details about roles, locations, and organizational structure within an educational or community context

No Comments

No Known Activations