INDEX

Explanations

references to principles and concepts related to ethical or guiding frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

esco

-0.16

nemonic

-0.16

akan

-0.15

rou

-0.15

ç¹Ķ

-0.15

arus

-0.15

dur

-0.15

izen

-0.15

akk

-0.14

ABILITY

-0.14

POSITIVE LOGITS

ps

0.18

/pr

0.18

stown

0.17

apore

0.17

 principles

0.16

chaft

0.15

/Foundation

0.15

-ÑĤÐ¾

0.15

pal

0.15

 principle

0.15

Activations Density 0.019%

references to principles and concepts related to ethical or guiding frameworks

No Comments

No Known Activations