INDEX

Explanations

references to models and modeling in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

keit

-0.21

lander

-0.16

enne

-0.15

ream

-0.15

dar

-0.15

rer

-0.15

ath

-0.15

odes

-0.14

nes

-0.14

 Uber

-0.14

POSITIVE LOGITS

led

0.21

-model

0.18

.Model

0.18

mapper

0.17

=model

0.17

ë§ģ

0.16

ocked

0.16

AndView

0.15

/model

0.15

.addAttribute

0.15

Activations Density 0.050%

references to models and modeling in various contexts

No Comments

No Known Activations