INDEX

Explanations

references to the concept of "full" or complete narratives and reports

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

spi

-0.15

linger

-0.15

tera

-0.15

wap

-0.14

äºĨä¸Ģ

-0.14

 altogether

-0.14

arrants

-0.14

gression

-0.14

umbed

-0.13

abinet

-0.13

POSITIVE LOGITS

\Php

0.15

tas

0.15

ras

0.14

ÙĬÙĥÙĬ

0.14

kÃ¼

0.14

forge

0.14

avn

0.14

 Ú¯Ø±

0.14

pek

0.14

Activations Density 0.034%

references to the concept of "full" or complete narratives and reports

No Comments

No Known Activations