INDEX

Explanations

instances of the word "down" followed by directional phrases or references to locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

agu

-0.17

pollo

-0.17

quier

-0.17

AdapterManager

-0.16

kola

-0.15

 Ð¿ÑĢÐ¸Ðº

-0.15

HeaderCode

-0.15

anuts

-0.15

mana

-0.15

posal

-0.15

POSITIVE LOGITS

arto

0.16

esar

0.15

 truck

0.15

ann

0.15

 Diss

0.15

wind

0.15

 hall

0.14

ent

0.14

iro

0.14

fen

0.14

Activations Density 0.021%

instances of the word "down" followed by directional phrases or references to locations

No Comments

No Known Activations