INDEX

Explanations

references to rankings or ratings, particularly in a hierarchical context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

essel

-0.15

ymous

-0.15

erv

-0.15

ennes

-0.14

ym

-0.14

iej

-0.14

rael

-0.14

ector

-0.14

omnia

-0.13

elf

-0.13

POSITIVE LOGITS

foot

0.15

erer

0.15

riott

0.14

erah

0.14

ÏĤ

0.14

ls

0.14

ozem

0.14

 Carlton

0.13

ola

0.13

logger

0.13

Activations Density 0.014%

references to rankings or ratings, particularly in a hierarchical context

No Comments

No Known Activations