INDEX

Explanations

data related to fossil analysis and validation

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

Å¡ti

-0.17

esson

-0.16

heit

-0.16

ectl

-0.16

elda

-0.16

æĦı

-0.15

 belki

-0.15

à¸±à¸Ī

-0.15

roke

-0.14

obuf

-0.14

POSITIVE LOGITS

 observed

0.19

 indirect

0.16

 signs

0.16

gram

0.15

aux

0.15

lint

0.15

imar

0.15

erland

0.15

agram

0.14

 evidence

0.14

Activations Density 0.221%

data related to fossil analysis and validation

No Comments

No Known Activations