INDEX

Explanations

instances of users' interaction and feedback in forum discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

).__

-0.17

eks

-0.15

anker

-0.15

 Gunn

-0.14

angible

-0.14

sit

-0.14

ortho

-0.14

rear

-0.14

 spoil

-0.14

Overflow

-0.13

POSITIVE LOGITS

 Ð¿ÐµÑĢÐµÐ´Ð°

0.15

ovies

0.15

Âłmi

0.14

 cowboy

0.14

udoku

0.14

 Battles

0.14

otron

0.14

ritten

0.14

 eens

0.14

ERGY

0.14

Activations Density 0.017%

instances of users' interaction and feedback in forum discussions

No Comments

No Known Activations