INDEX

Explanations

possessive forms of nouns indicating ownership or association

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

olen

-0.16

imed

-0.14

Nim

-0.14

parent

-0.14

è²¡

-0.14

 Stewart

-0.13

ä½µ

-0.13

oÅĪ

-0.13

ture

-0.13

ws

-0.13

POSITIVE LOGITS

Æ¯á»

0.16

ulls

0.15

Uvs

0.14

obo

0.14

ulling

0.14

noop

0.14

rray

0.14

_cipher

0.14

 Edition

0.13

adÃŃ

0.13

Activations Density 0.165%

possessive forms of nouns indicating ownership or association

No Comments

No Known Activations