INDEX

Explanations

statements related to discoveries or occurrences of individuals or objects, particularly in a context of crime or missing persons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ÑĢÐ°Ñĩ

-0.14

å¼

-0.14

uant

-0.14

RNG

-0.14

anson

-0.14

ÑĪÐ¸Ð±

-0.13

 Clem

-0.13

allax

-0.13

Ð»Ð°ÑĤ

-0.13

 punching

-0.13

POSITIVE LOGITS

_easy

0.14

PE

0.14

stag

0.14

EventManager

0.14

avis

0.14

Ã©al

0.14

 Ø§ÙĦØªÙĪ

0.13

sol

0.13

ena

0.13

ë¹

0.13

Activations Density 0.047%

statements related to discoveries or occurrences of individuals or objects, particularly in a context of crime or missing persons

No Comments

No Known Activations