INDEX

Explanations

technical jargon and formal language related to processes and definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

tit

-0.14

Liv

-0.14

archs

-0.14

elu

-0.14

rint

-0.13

asts

-0.13

kest

-0.13

 fasc

-0.13

 Sage

-0.13

worksheet

-0.13

POSITIVE LOGITS

Ont

0.33

ont

0.32

Ont

0.31

 ontology

0.28

ont

0.28

sem

0.28

onto

0.27

_sem

0.26

ontology

0.25

.sem

0.25

Activations Density 0.058%

technical jargon and formal language related to processes and definitions

No Comments

No Known Activations