INDEX

Explanations

details regarding product features and specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

asan

-0.15

ceptar

-0.14

inders

-0.14

stdarg

-0.14

.Toolkit

-0.13

ior

-0.13

undi

-0.13

 nháº¯c

-0.13

 sÃ¦

-0.13

 nors

-0.13

POSITIVE LOGITS

 thereby

0.52

 thus

0.48

 resulting

0.41

thus

0.41

 meaning

0.39

 making

0.39

 Thus

0.33

 leaving

0.33

 allowing

0.32

 giving

0.32

Activations Density 0.777%

details regarding product features and specifications

No Comments

No Known Activations