INDEX

Explanations

concepts related to scientific reasoning and philosophical arguments

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

elu

-0.21

typeorm

-0.16

 primal

-0.15

 ExecutionContext

-0.15

dech

-0.15

uo

-0.14

hrad

-0.14

ovement

-0.14

decode

-0.14

lexical

-0.14

POSITIVE LOGITS

 induction

0.26

 fals

0.26

 observation

0.23

 deduct

0.22

Ded

0.21

emp

0.21

 indu

0.20

Pop

0.19

 experiment

0.19

 observations

0.19

Activations Density 0.120%

concepts related to scientific reasoning and philosophical arguments

No Comments

No Known Activations

concepts related to scientific reasoning and philosophical arguments

No Comments

No Known Activations