INDEX

Explanations

references to spherical objects and concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ÐµÐ´Ð¸Ð½Ð¸

-0.15

yr

-0.15

empo

-0.14

ataka

-0.14

abyrin

-0.14

ein

-0.14

orious

-0.14

opia

-0.14

ted

-0.14

 ê°¤

-0.13

POSITIVE LOGITS

folio

0.16

 Leer

0.15

uld

0.15

cilik

0.15

iten

0.15

 DBNull

0.15

itto

0.14

curity

0.14

ÅĻiv

0.14

ker

0.14

Activations Density 0.027%

references to spherical objects and concepts

No Comments

No Known Activations