INDEX

Explanations

specific names and references related to various organizations, events, and notable individuals in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

imals

-0.15

idity

-0.14

rella

-0.13

isma

-0.13

ncy

-0.13

pedia

-0.13

à¹Ħà¸£

-0.13

.roll

-0.13

wick

-0.13

wat

-0.13

POSITIVE LOGITS

to

0.53

 name

0.41

 mention

0.37

 among

0.33

 Mention

0.31

 amongst

0.30

mention

0.30

to

0.30

 Name

0.29

 mentions

0.29

Activations Density 0.097%

specific names and references related to various organizations, events, and notable individuals in different contexts

No Comments

No Known Activations