INDEX

Explanations

references to authority and official statements in a news context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Vtbl

-0.15

 flown

-0.14

.visualization

-0.13

merged

-0.13

Installed

-0.12

Intialized

-0.12

 undergone

-0.12

 ÑĥÑģÑĤÐ°Ð½Ð¾Ð²Ð»ÐµÐ½

-0.12

 eaten

-0.12

 GENERATED

-0.12

POSITIVE LOGITS

 said

0.46

 stated

0.40

 commented

0.38

 remarked

0.38

 explained

0.37

 told

0.35

said

0.35

 says

0.34

 noted

0.32

 pointed

0.32

Activations Density 2.409%

references to authority and official statements in a news context

No Comments

No Known Activations