INDEX

Explanations

references to decision-making processes and future plans

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

atern

-0.15

iler

-0.15

_mono

-0.14

Ð¾Ð·Ð¼Ð¾Ð¶Ð½Ð¾

-0.14

 Levin

-0.14

.raise

-0.14

eds

-0.13

eroon

-0.13

 Submit

-0.13

mini

-0.13

POSITIVE LOGITS

agua

0.15

ServletRequest

0.15

uft

0.14

marshall

0.14

'=>['

0.14

ÙĤÛĮ

0.14

ixmap

0.13

ichten

0.13

infeld

0.13

Activations Density 0.249%

references to decision-making processes and future plans

No Comments

No Known Activations