INDEX

Explanations

references to awards and honors in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

-0.15

 ÑĢÑĥÐ±

-0.14

ESA

-0.13

ani

-0.13

EO

-0.13

Serialization

-0.13

uby

-0.13

igu

-0.13

 tÃ¤

-0.13

é¹

-0.13

POSITIVE LOGITS

abelle

0.16

akit

0.16

ifest

0.15

inton

0.14

Ã³Å¼

0.14

ingt

0.14

hte

0.14

otre

0.14

rlen

0.14

kontakte

0.13

Activations Density 0.160%

references to awards and honors in various contexts

No Comments

No Known Activations