INDEX

Explanations

phrases that indicate the concept of causation or condition leading to an outcome

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ovation

-0.15

 resil

-0.14

 Lens

-0.14

 indem

-0.14

 Gors

-0.13

pery

-0.13

apyrus

-0.13

iras

-0.13

 Lamp

-0.13

POSITIVE LOGITS

artz

0.17

Argb

0.16

WT

0.15

TPL

0.14

adastro

0.14

adil

0.14

ared

0.14

 maxi

0.14

ë·

0.14

Activations Density 0.026%

phrases that indicate the concept of causation or condition leading to an outcome

No Comments

No Known Activations